Dual-systems frameworks propose that moral judgments are derived from both an immediate emotional response, and controlled/rational cognition. Recently Cushman (2013) proposed a new dual-system theory based on model-free and model-based reinforcement learning. Model-free learning attaches values to actions based on their history of reward and punishment, and explains some deontological, non-utilitarian judgments. Model-based learning involves the construction of a causal model of the world and allows for far-sighted planning; this form (...) of learning fits well with utilitarian considerations that seek to maximize certain kinds of outcomes. I present three concerns regarding the use of model-free reinforcement learning to explain deontological moral judgment. First, many actions that humans find aversive from model-free learning are not judged to be morally wrong. Moral judgment must require something in addition to model-free learning. Second, there is a dearth of evidence for central predictions of the reinforcement account—e.g., that people with different reinforcement histories will, all else equal, make different moral judgments. Finally, to account for the effect of intention within the framework requires certain assumptions which lack support. These challenges are reasonable foci for future empirical/theoretical work on the model-free/model-based framework. (shrink)

Theories of decision-making and its neural substrates have long assumed the existence of two distinct and competing valuation systems, variously described as goal-directed vs. habitual, or, more recently and based on statistical arguments, as model-free vs. model-based reinforcement-learning. Though both have been shown to control choices, the cognitive abilities associated with these systems are under ongoing investigation. Here we examine the link to cognitive abilities, and find that individual differences in processing speed covary with a shift (...) from model-free to model-based choice control in the presence of above-average working memory function. This suggests shared cognitive and neural processes; provides a bridge between literatures on intelligence and valuation; and may guide the development of process models of different valuation components. Furthermore, it provides a rationale for individual differences in the tendency to deploy valuation systems, which may be important for understanding the manifold neuropsychiatric diseases associated with malfunctions of valuation. (shrink)

A novel data-driven model-free adaptive control approach is first proposed by combining the advantages of model-free adaptive control and data-driven optimal iterative learning control, and then its stability and convergence analysis is given to prove algorithm stability and asymptotical convergence of tracking error. Besides, the parameters of presented approach are adaptively adjusted with fuzzy logic to determine the occupied proportions of MFAC and DDOILC according to their different control performances in different control stages. Lastly, the (...) proposed fuzzy DDMFAC approach is applied to the control of particle quality in drug development phase of spray fluidized-bed granulation process, and its control effect is compared with MFAC and DDOILC and their fuzzy forms, in which the parameters of MFAC and DDOILC are adaptively adjusted with fuzzy logic. The effectiveness of the presented FDDMFAC approach is verified by a series of simulations. (shrink)

The author proposes a neural-network-based explanation of how a brain might acquire intuitive expertise. The explanation is intended merely to be suggestive and lacks many complexities found in even lower animal brains. Yet significantly, even this simplified brain model is capable of explaining the acquisition of simple skills without developing articulable rules for behavior or a model of the skill domain or an explicit identification of which observables in the environment are necessary for skillful behavior. Furthermore, no memories (...) of prior experiences during the learning phase are explicitly stored and accessed during behavior. The explanation thus calls into doubt many conventional and intuitively reasonable assumptions concerning the learning and production of intuitive expertise. (shrink)

Violence suffered by children is a violation of human rights and a global health problem. Children with disabilities are especially vulnerable to violence in the school environment, which has a negative impact on their well-being and health. Students with disabilities educated in special schools have, in addition, more reduced experiences of interaction that may reduce both their opportunities for learning and for building protective social networks of support. This study analyses the transference of evidence-based actions to prevent violence in (...) schools – the dialogic model of prevention and resolution of conflicts (DMPRC) – in the context of a special school, and its impact on the reduction of violence, the creation of egalitarian relationships, and the prevention of bullying. A case study with a communicative approach was conducted including in-depth interviews and communicative focus groups with the diverse participants to analyze the process of transformation carried out in the school and the main actions that give students a voice in the management and creation of egalitarian non-violent relationships. The results show that the inclusion of the students’ voices in the resolution and prevention of conflicts reduces violence, empowers special education students, strengthens friendship relationships, caring behavior, and active positioning among the community. The positive impact of the transference of the DMPRC to special schools contributes to students’ well-being and healthy development by offering safe and protective educational spaces and quality emotional education, also contributing to the achievement of the Sustainable Development Goals related to the elimination of all forms of violence in childhood. (shrink)

In this paper we address the modelling of reasoning processes in natural agents. We focus on a very basic kind of non-monotonic inference for which we identify a simple and plausible underlying process, and we develop a family of logical models that allow to match this process. Partial worlds models, as we call them, are a variant of Kraus, Lehmann and Magidor’s cumulative models. We show that the inference relations they induce form a strict subclass of cumulative relations and tackle (...) the issue of providing sound and complete sets of rules to characterise them. Taking inspiration from the work of Gabbay and Schlechta, we analyse the question in terms of definable sets of partial worlds and conclude that completeness is probably unreachable using a standard propositional language. This brings us to enrich our language with an additional connective, which makes it possible to distinguish between two kinds of disjunction in the partial worlds context. Within this renewed framework, we provide two representation theorems: one for inference relations induced by precisification-free smooth models, and the other for inference relations induced by precisification-free ranked models. Finally we give an aperçu of how partial worlds models lend themselves to the modelling of learning. (shrink)

In this article, we propose a new method to learn the underlying acyclic mixed graph of a linear non-Gaussian structural equation model with given observational data. We build on an algorithm proposed by Wang and Drton, and we show that one can augment the hidden variable structure of the recovered model by learning multidirected edges rather than only directed and bidirected ones. Multidirected edges appear when more than two of the observed variables have a hidden common cause. (...) We detect the presence of such hidden causes by looking at higher order cumulants and exploiting the multi-trek rule. Our method recovers the correct structure when the underlying graph is a bow-free acyclic mixed graph with potential multidirected edges. (shrink)

This paper argues that a well known passage from Plato’s Meno exemplifies how to employ scaffolded learning in the philosophy classroom. It explores scaffolded learning by fully defining it, explaining it, and gesturing at some ways in which scaffolding has been implemented. We then offer our own model of scaffolded learning in terms of four phases and eight stages, and explicate our model using a well known example from Plato’s Meno as an exemplar. We believe (...) that any practical concerns one might have against the employment of scaffolded learning in the philosophy classroom ought not serve as an impediment to adopting our model. (shrink)

The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing parallels to the philosophy of induction, we point out that the no-free-lunch results presuppose a conception of learning algorithms as purely data-driven. On this conception, every algorithm must have an inherent inductive bias, that wants justification. We argue that many (...) standard learning algorithms should rather be understood as model-dependent: in each application they also require for input a model, representing a bias. Generic algorithms themselves, they can be given a model-relative justification. (shrink)

Machine learning (ML) refers to a class of computer-facilitated methods of statistical modelling. ML modelling techniques are now being widely adopted across the sciences. A number of outspoken representatives from the general public, computer science, various scientific fields, and philosophy of science alike seem to share in the belief that ML will radically disrupt scientific practice or the variety of epistemic outputs science is capable of producing. Such a belief is held, at least in part, because its adherents take (...) ML to exist on novel epistemic footing relative to classical mathematical or statistical modelling approaches utilised in science. Namely, they take modelling with ML to be a “theory-free” enterprise, in the sense of not resting essentially on input from human conceptual grasp on the target phenomenon and domain expertise. I take this view to arise from the further, and more deeply entrenched belief that data is worldly and objective; i.e., data is viewed as recapitulating or representing with perfect fidelity the structure or properties of the systems in nature it is sampled from. Yet most contemporary philosophers of science take on board, in one version or other, the thesis of theory-ladenness or theory-mediation of observation or measurement. From this, it follows that most philosophers of science (and, I will venture, many scientists) hold irreconcilable views on the nature of data, an internal tension which threatens the integrity of their appraisals of ML in science. Taking the thesis of theory-ladenness on board---and its implications for the nature of data seriously---it follows that there is no reason to believe that ML differs fundamentally in its epistemic footing from established mathematical modelling approaches in the sciences. I show that usage and interpretation can differ from “standard practice” in scientific projects which wield the tools of ML without accepting a difference in the epistemic or representational status of such tools. (shrink)

An evolutionary case for the existence of free will. Scientists are learning more and more about how brain activity controls behavior and how neural circuits weigh alternatives and initiate actions. As we probe ever deeper into the mechanics of decision making, many conclude that agency-or free will-is an illusion. In Free Agents, leading neuroscientist Kevin Mitchell presents a wealth of evidence to the contrary, arguing that we are not mere machines responding to physical forces but agents (...) acting with purpose. Traversing billions of years of evolution, Mitchell tells the remarkable story of how living beings capable of choice emerged from lifeless matter. He explains how the emergence of nervous systems provided a means to learn about the world, granting sentient animals the capacity to model, predict, and simulate. Mitchell reveals how these faculties reached their peak in humans with our abilities to imagine and to introspect, to reason in the moment, and to shape our possible futures through the exercise of our individual agency. Mitchell's argument has important implications-for how we understand decision making, for how our individual agency can be enhanced or infringed, for how we think about collective agency in the face of global crises, and for how we consider the limitations and future of artificial intelligence.An astonishing journey of discovery, Free Agents offers a new framework for understanding how, across a billion years of Earth history, life evolved the power to choose and why this matters. (shrink)

Supraspan verbal list-learning tests, such as the Rey Auditory Verbal Learning Test (RAVLT), are classic neuropsychological tests for assessing verbal memory. In this study, we investigated the impact of the meaning of the words to be learned on 3 memory stages (short-term recall, learning, and delayed recall) in a cohort of 447 healthy adults. First, we compared scores obtained from the RAVLT (word condition) to those of an alternative version of this test using phonologically similar but meaningless (...) items (pseudoword condition) and observed how each score varied as a function of age and sex. Then, we collected the participants’ self-reported strategies to retain the word and pseudoword lists and examined if these strategies mediated the age and sex effects on memory scores. The word condition resulted in higher memory scores than pseudoword condition at each memory stage and even canceled out, for the learning stage, the detrimental effect of age that was observed for the short-term and delayed recall. When taking sex into account, the word advantage was observed only in women for short-term recall. The self-reported strategies, which were similar for words and pseudowords, were based on the position of the item on the list (word: 53 %, pseudoword: 37%) or the meaning of the item (word: 64%, pseudoword: 58%) and were used alone or in combination. The best memory performance was associated with the meaning strategy in the word condition and with the combination of the meaning and position strategies in the pseudoword condition. Finally, we found that the word advantage observed in women for short-term recall was mediated by the use of the meaning strategy. The RAVLT scores were thus highly dependent on word meaning, notably because it allowed efficient semantic knowledge-based strategies. Within the framework of Tulving’s declarative memory model, these results are at odds with the depiction of the RAVLT as a verbal episodic memory test as it is increasingly referred to in the literature. (shrink)

Subjects exposed to strings of letters generated by a finite state grammar can later classify grammatical and nongrammatical test strings, even though they cannot adequately say what the rules of the grammar are (e.g., Reber, 1989). The MINERVA 2 (Hintzman, 1986) and Medin and Schaffer (1978) memory‐array models and a number of connectionist outoassociator models are tested against experimental data by deriving mainly parameter‐free predictions from the models of the rank order of classification difficulty of test strings. The importance (...) of different assumptions regarding the coding of features (How should the absence of a feature be coded? Should single letters or digrams be coded?), the learning rule used (Hebb rule vs. delta rule), and the connectivity (Should features be predicted only by previous features in the string, or by all features simultaneously?) is investigated by determining the performance of the models with and without each assumption. Only one class of connectionist model (the simultaneous delta rule) passes all the tests. It is shown that this class of model can be regarded by abstracting a set of representative but incomplete rules of the grammar. (shrink)

If one formulates Helmholtz's ideas about perception in terms of modern-day theories one arrives at a model of perceptual inference and learning that can explain a remarkable range of neurobiological facts. Using constructs from statistical physics it can be shown that the problems of inferring what cause our sensory inputs and learning causal regularities in the sensorium can be resolved using exactly the same principles. Furthermore, inference and learning can proceed in a biologically plausible fashion. The (...) ensuing scheme rests on Empirical Bayes and hierarchical models of how sensory information is generated. The use of hierarchical models enables the brain to construct prior expectations in a dynamic and context-sensitive fashion. This scheme provides a principled way to understand many aspects of the brain's organisation and responses. In this paper, we suggest that these perceptual processes are just one emergent property of systems that conform to a free-energy principle. The free-energy considered here represents a bound on the surprise inherent in any exchange with the environment, under expectations encoded by its state or configuration. A system can minimise free-energy by changing its configuration to change the way it samples the environment, or to change its expectations. These changes correspond to action and perception, respectively, and lead to an adaptive exchange with the environment that is characteristic of biological systems. This treatment implies that the system's state and structure encode an implicit and probabilistic model of the environment. We will look at models entailed by the brain and how minimisation of free-energy can explain its dynamics and structure. (shrink)

This article describes the potential impact that free (i.e., open source) software can have on an existing commercial software market. A model for the software market is constructed in terms of autonomous agents, which represent the users, the companies, and the free software providers. The model specifies a reservation price for each user agent and develops a gradient learning strategy for revenue-maximizing company agents. Simulations explore parameters such as the demand distribution, and the relative importance (...) of market share, advertising and random effects in product visibility. Results from the case without free software show a prevalence of monopolies, which is consistent with other studies of high-technology market economics. The effects of free software are not uniform, but are highly parameter dependent. A “capture region” is found in which free software eventually dominates the market. (shrink)

There is substantial variation in language experience, yet there is surprising similarity in the language structure acquired. Constraints on language structure may be external modulators that result in this canalization of language structure, or else they may derive from the broader, communicative environment in which language is acquired. In this paper, the latter perspective is tested for its adequacy in explaining robustness of language learning to environmental variation. A computational model of word learning from cross-situational, multimodal information (...) was constructed and tested. Key to the model's robustness was the presence of multiple, individually unreliable information sources to support learning. This “degeneracy” in the language system has a detrimental effect on learning, compared to a noise-free environment, but has a critically important effect on acquisition of a canalized system that is resistant to environmental noise in communication. (shrink)

Lake et al. propose three criteria which, they argue, will bring artificial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine (...) class='Hi'>learning. We also discuss how work in embodied and situated cognition could provide a valu- able perspective on future research. (shrink)

There is substantial variation in language experience, yet there is surprising similarity in the language structure acquired. Constraints on language structure may be external modulators that result in this canalization of language structure, or else they may derive from the broader, communicative environment in which language is acquired. In this paper, the latter perspective is tested for its adequacy in explaining robustness of language learning to environmental variation. A computational model of word learning from cross-situational, multimodal information (...) was constructed and tested. Key to the model's robustness was the presence of multiple, individually unreliable information sources to support learning. This “degeneracy” in the language system has a detrimental effect on learning, compared to a noise-free environment, but has a critically important effect on acquisition of a canalized system that is resistant to environmental noise in communication. (shrink)

The mesostriatal dopamine system is prominently implicated in model-free reinforcement learning, with fMRI BOLD signals in ventral striatum notably covarying with model-free prediction errors. However, latent learning and devaluation studies show that behavior also shows hallmarks of model-based planning, and the interaction between model-based and model-free values, prediction errors, and preferences is underexplored. We designed a multistep decision task in which model-based and model-free influences on human choice (...) behavior could be distinguished. By showing that choices reflected both influences we could then test the purity of the ventral striatal BOLD signal as a model-free report. Contrary to expectations, the signal reflected both model-free and model-based predictions in proportions matching those that best explained choice behavior. These results challenge the notion of a separate model-free learner and suggest a more integrated computational architecture for high-level human decision-making. (shrink)

Theoretical models are widely held as sources of knowledge of reality. Imagination is vital to their development and to the generation of plausible hypotheses about reality. But how can imagination, which is typically held to be completely free, effectively instruct us about reality? In this paper I argue that the key to answering this question is in constrained uses of imagination. More specifically, I identify make-believe as the right notion of imagination at work in modelling. I propose the first (...) overarching taxonomy of types of constraints on scientific imagination that enables knowledge of reality. And I identify two main kinds of knowledge enabled by models, knowledge of the imaginary scenario specified by models and knowledge of reality. (shrink)

This paper reconsiders the diphone-based word segmentation model of Cairns, Shillcock, Chater, and Levy (1997) and Hockema (2006), previously thought to be unlearnable. A statistically principled learning model is developed using Bayes’ theorem and reasonable assumptions about infants’ implicit knowledge. The ability to recover phrase-medial word boundaries is tested using phonetic corpora derived from spontaneous interactions with children and adults. The (unsupervised and semi-supervised) learning models are shown to exhibit several crucial properties. First, only a small (...) amount of language exposure is required to achieve the model’s ceiling performance, equivalent to between 1 day and 1 month of caregiver input. Second, the models are robust to variation, both in the free parameter and the input representation. Finally, both the learning and baseline models exhibit undersegmentation, argued to have significant ramifications for speech processing as a whole. (shrink)

If one formulates Helmholtz’s ideas about perception in terms of modern-day theories one arrives at a model of perceptual inference and learning that can explain a remarkable range of neurobiological facts. Using constructs from statistical physics it can be shown that the problems of inferring what cause our sensory inputs and learning causal regularities in the sensorium can be resolved using exactly the same principles. Furthermore, inference and learning can proceed in a biologically plausible fashion. The (...) ensuing scheme rests on Empirical Bayes and hierarchical models of how sensory information is generated. The use of hierarchical models enables the brain to construct prior expectations in a dynamic and context-sensitive fashion. This scheme provides a principled way to understand many aspects of the brain’s organisation and responses. In this paper, we suggest that these perceptual processes are just one emergent property of systems that conform to a free-energy principle. The free-energy considered here represents a bound on the surprise inherent in any exchange with the environment, under expectations encoded by its state or configuration. A system can minimise free-energy by changing its configuration to change the way it samples the environment, or to change its expectations. These changes correspond to action and perception, respectively, and lead to an adaptive exchange with the environment that is characteristic of biological systems. This treatment implies that the system’s state and structure encode an implicit and probabilistic model of the environment. We will look at models entailed by the brain and how minimisation of free-energy can explain its dynamics and structure. (shrink)

While rules and exemplars are usually viewed as opposites, this paper argues that they form end points of the same distribution. By representing both rules and exemplars as (partial) trees, we can take into account the fluid middle ground between the two extremes. This insight is the starting point for a new theory of language learning that is based on the following idea: If a language learner does not know which phrase‐structure trees should be assigned to initial sentences, s/he (...) allows (implicitly) for all possible trees and lets linguistic experience decide which is the “best” tree for each sentence. The best tree is obtained by maximizing “structural analogy” between a sentence and previous sentences, which is formalized by the most probable shortest combination of subtrees from all trees of previous sentences. Corpus‐based experiments with this model on the Penn Treebank and the Childes database indicate that it can learn both exemplar‐based and rule‐based aspects of language, ranging from phrasal verbs to auxiliary fronting. By having learned the syntactic structures of sentences, we have also learned the grammar implicit in these structures, which can in turn be used to produce new sentences. We show that our model mimicks children’s language development from item‐based constructions to abstract constructions, and that the model can simulate some of the errors made by children in producing complex questions. (shrink)

To date, game-based learning programs that include comprehensive creativity skills and disposition training are still very limited. The present researchers developed a comprehensive game-based creativity learning program for fifth and sixth grade pupils. Further analysis presented relationship trends between mindful learning experience, flow experience, self-efficacy, and mastery experience. Eighty-three 5th and 6th grade participants undertook the six-week game-based creativity learning program. Upon the completion of experimental instruction, those who scored higher on the concerned variables improved more (...) in self-evaluation of both creativity ability and confidence, than their counterparts. Additionally, path model analysis revealed that mindful learning experience was a powerful predictor of both mastery experience and flow experience; it also influenced mastery experience through flow experience and self-efficacy during game-based creativity learning. The findings support the effectiveness of the game-based learning program developed in this study. Moreover, this study contributes to the theoretical construction of how game-based learning can be designed to facilitate mindful learning experience, flow experience, self-efficacy, and mastery experience during creativity training among pupils. Effective mechanisms include providing rewards for high-quality performance, challenging tasks, free choices of design components, immediate feedback, and idea sharing. The profound theoretical framework proposed in this study provides a valuable approach for creativity instruction through game-based learning or classroom instruction. (shrink)

Model theory is the branch of mathematical logic looking at the relationship between mathematical structures and logic languages. These formal languages are free from the ambiguities of natural languages, and are becoming increasingly important in areas such as computing, philosophy and linguistics. This book provides a clear introduction to the subject for both mathematicians and the non-specialists now needing to learn some model theory.

Sequential action makes up the bulk of human daily activity, and yet much remains unknown about how people learn such actions. In one motor learning paradigm, the serial reaction time (SRT) task, people are taught a consistent sequence of button presses by cueing them with the next target response. However, the SRT task only records keypress response times to a cued target, and thus it cannot reveal the full time‐course of motion, including predictive movements. This paper describes a mouse (...) movement trajectory SRT task in which the cursor must be moved to a cued location. We replicated keypress SRT results, but also found that predictive movement—before the next cue appears—increased during the experiment. Moreover, trajectory analyses revealed that people developed a centering strategy under uncertainty. In a second experiment, we made prediction explicit, no longer cueing targets. Thus, participants had to explore the response alternatives and learn via reinforcement, receiving rewards and penalties for correct and incorrect actions, respectively. Participants were not told whether the sequence of stimuli was deterministic, nor if it would repeat, nor how long it was. Given the difficulty of the task, it is unsurprising that some learners performed poorly. However, many learners performed remarkably well, and some acquired the full 10‐item sequence within 10 repetitions. Comparing the high‐ and low‐performers’ detailed results in this reinforcement learning (RL) task with the first experiment's cued trajectory SRT task, we found similarities between the two tasks, suggesting that the effects in Experiment 1 are due to predictive, rather than reactive processes. Finally, we found that two standard model‐free reinforcement learning models fit the high‐performing participants, while the four low‐performing participants provide better fit with a simple negative recency bias model. (shrink)

Sequential action makes up the bulk of human daily activity, and yet much remains unknown about how people learn such actions. In one motor learning paradigm, the serial reaction time (SRT) task, people are taught a consistent sequence of button presses by cueing them with the next target response. However, the SRT task only records keypress response times to a cued target, and thus it cannot reveal the full time‐course of motion, including predictive movements. This paper describes a mouse (...) movement trajectory SRT task in which the cursor must be moved to a cued location. We replicated keypress SRT results, but also found that predictive movement—before the next cue appears—increased during the experiment. Moreover, trajectory analyses revealed that people developed a centering strategy under uncertainty. In a second experiment, we made prediction explicit, no longer cueing targets. Thus, participants had to explore the response alternatives and learn via reinforcement, receiving rewards and penalties for correct and incorrect actions, respectively. Participants were not told whether the sequence of stimuli was deterministic, nor if it would repeat, nor how long it was. Given the difficulty of the task, it is unsurprising that some learners performed poorly. However, many learners performed remarkably well, and some acquired the full 10‐item sequence within 10 repetitions. Comparing the high‐ and low‐performers’ detailed results in this reinforcement learning (RL) task with the first experiment's cued trajectory SRT task, we found similarities between the two tasks, suggesting that the effects in Experiment 1 are due to predictive, rather than reactive processes. Finally, we found that two standard model‐free reinforcement learning models fit the high‐performing participants, while the four low‐performing participants provide better fit with a simple negative recency bias model. (shrink)

Occam’s razor directs us to adopt the simplest hypothesis consistent with the evidence. Learning theory provides a precise definition of the inductive simplicity of a hypothesis for a given learning problem. This definition specifies a learning method that implements an inductive version of Occam’s razor. As a case study, we apply Occam’s inductive razor to causal learning. We consider two causal learning problems: learning a causal graph structure that presents global causal connections among a (...) set of domain variables, and learning context-sensitive causal relationships that hold not globally, but only relative to a context. For causal graph learning, Occam’s inductive razor directs us to adopt the model that explains the observed correlations with a minimum number of direct causal connections. For expanding a causal graph structure to include context-sensitive relationships, Occam’s inductive razor directs us to adopt the expansion that explains the observed correlations with a minimum number of free parameters. This is equivalent to explaining the correlations with a minimum number of probabilistic logical rules. The paper provides a gentle introduction to the learning-theoretic definition of inductive simplicity and the application of Occam’s razor for causal learning. (shrink)

Free will, which is dealt with under the title of "acts of the servants" in the Kalām literature, is one of the fundamental issues of the science of Kalām. Benjamin Libet's famous experiment, which he conducted in order to seek an answer to the question of free will, caused the free will debates to move to the field of neuroscience. The logic of Libet's experiment is to compare the neural activity in the brain with the moment when (...) a person is conscious while performing a voluntary act. In Libet's subjects, it was observed that brain activity in the decision-making process started at the moment of unconsciousness. The results of this experiment have long been interpreted in neuroscience as showing that free will is an illusion. Although Libet claimed that conscious intention creates a veto effect by stopping the action at the last moment, recent studies have shown that Libet's veto solution for free will does not work. The most vocal critics of the implications of the Libet experiment from the beginning have generally been philosophers. In this article, the criticisms of the Libet experiments by names such as Marcel Brass, Alfred Mele, and Peter Ulric Tse are presented. However, especially in recent years, neuroscientist Aaron Schurger's experimental and mathematical reinterpretation of the concept of readiness potential, which is key for Libet, and his proposal of an alternative model are mentioned. The article discusses Schurger's claim that the readiness potential may not actually reflect a brain that is ready. According to Schurger, the readiness potential is just random fluctuations that already exist in the brain and is not the sole cause of decisions. In fact, it has been argued that the readiness potential is related to neural noise in the brain rather than to the decision-making process. Thanks to Schurger's critique and the new model, it became clear that the Libet experiment did not rule out free will. But it does not constitute a proof of free will either. While the subject remains a mystery, it is unthinkable for Kalām to remain aloof from these debates. The article also touches upon the views of the Jabriyya, Ash'ariyya, Maturidiyya and Mu'tazilah in Kalām regarding the acts of the servants and questions what the Libet experiment can mean for these schools. Accordingly, while Jabriyya, with its deterministic view, may correspond to an erroneous interpretation of the Libet experiment, Mutazila may be the school that will have the most difficulty in explaining the Libet experiment. As a result, it seems that the views that consider both human agency and God's creation in voluntary acts are the most accurate. Moreover, despite the lack of a clear explanation of the theory of kasb in the Ash'ariyya, the Maturidiyya's assertion that the juz'i will is uncreated and that two influences affect voluntary acts suggests that this school provides the most solid foundation for free will. In order for such discussions to proceed on a healthy basis, it is very important to follow multidisciplinary methods. In addition, as much as Kalāmists should approach scientific studies seriously, it is important that they do not adopt a completely submissive attitude in the face of scientific claims, and that they learn the relevant critiques from experts in the field. Only in this way, we believe that the scientific inferences to be made will be based on a solid ground and that Kalāmists can make serious contributions to the solution. (shrink)

This study tested four theoretical models of leadership with data from the ethnographic record. The first was a game-theoretical model of leadership in collective actions, in which followers prefer and reward a leader who monitors and sanctions free-riders as group size increases. The second was the dominance model, in which dominant leaders threaten followers with physical or social harm. The third, the prestige model, suggests leaders with valued skills and expertise are chosen by followers who strive (...) to emulate them. The fourth proposes that in small-scale, kin-based societies, men with high neural capital are best able to achieve and maintain positions of social influence (e.g., as headmen) and thereby often become polygynous and have more offspring than other men, which positively selects for greater neural capital. Using multiple search strategies we identified more than 1000 texts relevant to leadership in the Probability Sample of 60 cultures from the Human Relations Area Files (HRAF). We operationalized the model with variables and then coded all retrieved text records on the presence or absence of evidence for each of these 24 variables. We found mixed support for the collective action model, broad support for components of the prestige leadership style and the importance of neural capital and polygyny among leaders, but more limited support for the dominance leadership style. We found little evidence, however, of emulation of, or prestige-biased learning toward, leaders. We found that improving collective actions, having expertise, providing counsel, and being respected, having high neural capital, and being polygynous are common properties of leaders, which warrants a synthesis of the collective action, prestige, and neural capital and reproductive skew models. We sketch one such synthesis involving high-quality decision-making and other computational services. (shrink)

Linguistic and non-linguistic pattern learning have been studied separately, but we argue for a comparative approach. Analogous inductive problems arise in phonological and visual pattern learning. Evidence from three experiments shows that human learners can solve them in analogous ways, and that human performance in both cases can be captured by the same models. We test GMECCS, an implementation of the Configural Cue Model in a Maximum Entropy phonotactic-learning framework with a single free parameter, against (...) the alternative hypothesis that learners seek featurally simple algebraic rules. We study the full typology of patterns introduced by Shepard, Hovland, and Jenkins (), instantiated as both phonotactic patterns and visual analogs, using unsupervised training. Unlike SHJ, Experiments 1 and 2 found that both phonotactic and visual patterns that depended on fewer features could be more difficult than those that depended on more features, as predicted by GMECCS but not by rule-seeking. GMECCS also correctly predicted performance differences between stimulus subclasses within each pattern. A third experiment tried supervised training to elicit simple rule-seeking phonotactic learning, but cue-based behavior persisted. We conclude that similar cue-based cognitive processes are available for phonological and visual concept learning, and hence that studying either kind of learning can lead to significant insights about the other. (shrink)

Determining the knowledge that guides human judgments is fundamental to understanding how people reason, make decisions, and form predictions. We use an experimental procedure called ‘‘iterated learning,’’ in which the responses that people give on one trial are used to generate the data they see on the next, to pinpoint the knowledge that informs people's predictions about everyday events (e.g., predicting the total box office gross of a movie from its current take). In particular, we use this method to (...) discriminate between two models of human judgments: a simple Bayesian model (Griffiths & Tenenbaum, 2006) and a recently proposed alternative model that assumes people store only a few instances of each type of event in memory (MinK; Mozer, Pashler, & Homaei, 2008). Although testing these models using standard experimental procedures is difficult due to differences in the number of free parameters and the need to make assumptions about the knowledge of individual learners, we show that the two models make very different predictions about the outcome of iterated learning. The results of an experiment using this methodology provide a rich picture of how much people know about the distributions of everyday quantities, and they are inconsistent with the predictions of the MinK model. The results suggest that accurate predictions about everyday events reflect relatively sophisticated knowledge on the part of individuals. (shrink)

How can imitation lead to free musical expression? This article explores the role of auditory imitation in jazz. Even though many renowned jazz musicians have assessed the method of imitating recorded music, no systematic study has hitherto explored how the method prepares for aural jazz improvisation. The article uses Berliner's assumption that learning jazz by aural imitation is “just like” learning a mother tongue. The article studies three potential stages in the method, comparing them to the imitative, (...) rhythmic, multimodal, and protosymbolic behavior of infant perception (building on the works of Stern, Trevarthen, and Merleau-Ponty). The demonstrations of the aural imitation method draw on pedagogic experiences accumulated since 1979 at the Jazz Program at the Norwegian University of Science and Technology. By analyzing structures of behavior suggested by the method, the article indicates key traits that render aural jazz improvisation possible, such as a fundamental sense of rhythm, formation of symbolic behavior, joint musical attention, and the facility to “hear via the other.” In conclusion, we critically address a frequent theoretical model describing musical improvisation as a synthesis of discrete elements or building blocks. (shrink)

How can imitation lead to free musical expression? This article explores the role of auditory imitation in jazz. Even though many renowned jazz musicians have assessed the method of imitating recorded music, no systematic study has hitherto explored how the method prepares for aural jazz improvisation. The article picks up an assumption presented by Berliner (1994), suggesting that learning jazz by aural imitation is “just like” learning a mother tongue. The article studies three potential stages in the (...) method, comparing with imitative, rhythmic, multimodal, and protosymbolic behavior of infant perception (building on the works of Stern, Trevarthen, and Merleau-Ponty). The demonstrations of the aural-imitation method draw on pedagogic experiences accumulated since 1979 in the Jazz Program at the Norwegian University of Science and Technology. By analyzing structures of behavior suggested by the method, the article indicates key traits that render aural jazz improvisation possible, such as a fundamental sense of rhythm, formation of symbolic behavior, joint musical attention, and the facility to “hear via the other.” In conclusion, we critically address a frequent theoretical model describing musical improvisation as a synthesis of discrete elements or building blocks. (shrink)

Much has been written about the free energy principle (FEP), and much misunderstood. The principle has traditionally been put forth as a theory of brain function or biological self-organisation. Critiques of the framework have focused on its lack of empirical support and a failure to generate concrete, falsifiable predictions. I take both positive and negative evaluations of the FEP thus far to have been largely in error, and appeal to a robust literature on scientific modelling to rectify the situation. (...) A prominent account of scientific modelling distinguishes between model structure and model construal. I propose that the FEP be reserved to designate a model structure, to which philosophers and scientists add various construals, leading to a plethora of models based on the formal structure of the FEP. An entailment of this position is that demands placed on the FEP that it be falsifiable or that it conform to some degree of biological realism rest on a category error. To this end, I deliver first an account of the phenomenon of model transfer and the breakdown between model structure and model construal. In the second section, I offer an overview of the formal elements of the framework, tracing their history of model transfer and illustrating how the formalism comes apart from any interpretation thereof. Next, I evaluate existing comprehensive critical assessments of the FEP, and hypothesise as to potential sources of existing confusions in the literature. In the final section, I distinguish between what I hold to be the FEP—taken to be a modelling language or modelling framework—and what I term “FEP models.”. (shrink)

Experimental studies report positive effects of signing for language acquisition and communication in children with and without language development delays. However, little data are available on natural kindergarten settings. Therefore, our study used questionnaire data to investigate the sign learning in hearing children with and without language development delays in an inclusive kindergarten group with a co-enrolled deaf child and a deaf signing educator. We observed that the hearing children in this co-enrollment group learned more signs than the hearing (...) children from groups with only hearing educators who learned signs in a training program. Hearing children’s sign learning showed a tendency toward correlating positively with their level of spoken language development. However, the individual background for children with language development delays impacted this relationship. Additionally, we examined the modality use of all children in interactions with hearing and deaf educators and peers using questionnaire and video data. Despite acquiring signs, hearing children predominantly used spoken language with hearing educators and predominantly nonverbal communication strategies with the deaf educator and the deaf child. Children with language development delays used code-blending with hearing educators in a few cases. The deaf child used mainly sign language for interactions with the deaf educator and mainly nonverbal communication with hearing educators and peers. Overall, our results suggest that the presence of a deaf educator increases sign learning in hearing children. However, in interactions during free play, they barely used signs making it particularly challenging for the deaf child to participate. This reveals that, in addition to a deaf role model, more sign language competent peers and targeted approaches increasing the use of the visual modality are required. (shrink)

Distributional models of semantics learn word meanings from contextual co‐occurrence patterns across a large sample of natural language. Early models, such as LSA and HAL (Landauer & Dumais, 1997; Lund & Burgess, 1996), counted co‐occurrence events; later models, such as BEAGLE (Jones & Mewhort, 2007), replaced counting co‐occurrences with vector accumulation. All of these models learned from positive information only: Words that occur together within a context become related to each other. A recent class of distributional models, referred to as (...) neural embedding models, are based on a prediction process embedded in the functioning of a neural network: Such models predict words that should surround a target word in a given context (e.g., word2vec; Mikolov, Sutskever, Chen, Corrado, & Dean, 2013). An error signal derived from the prediction is used to update each word's representation via backpropagation. However, another key difference in predictive models is their use of negative information in addition to positive information to develop a semantic representation. The models use negative examples to predict words that should not surround a word in a given context. As before, an error signal derived from the prediction prompts an update of the word's representation, a procedure referred to as negative sampling. Standard uses of word2vec recommend a greater or equal ratio of negative to positive sampling. The use of negative information in developing a representation of semantic information is often thought to be intimately associated with word2vec's prediction process. We assess the role of negative information in developing a semantic representation and show that its power does not reflect the use of a prediction mechanism. Finally, we show how negative information can be efficiently integrated into classic count‐based semantic models using parameter‐free analytical transformations. (shrink)

Research on natural and artificial brains is proceeding at a rapid pace. However, the understanding of the essence of consciousness has changed slightly over the millennia, and only the last decade has brought some progress to the area. Scientific ideas emerged that the soul could be a product of the material body and that calculating machines could imitate brain processes. However, the authors of this book reject the previously common dualism—the view that the material and spiritual-psychic processes are separate and (...) require a completely different substance as their foundation. -/- Reductive Model of the Conscious Mind is a forward-thinking book wherein the authors identify processes that are the essence of conscious thinking and place them in the imagined, simplified structure of cells able to memorize and transmit information in the form of impulses, which they call neurons. The purpose of the study is to explain the essence of consciousness to the degree of development of natural sciences, because only the latter can find a way to embed the concept of the conscious mind in material brains. The book is divided into three parts. Part 1 works to convince readers that the emergence of consciousness does not require detailed knowledge of the structure and morphology of the brain, with the exception of some specific properties of the neural network structure that the authors attempt to point out. Part 2 proves that the biological structure of many natural brains fulfills the necessary conditions for consciousness and intelligent thinking. Similarly, Part 3 shows the ways in which artificial creatures imitating natural brains can meet these conditions, which gives great hopes for building artificially intelligent beings endowed with consciousness. Covering topics that include cognitive architecture, the embodied mind, and machine learning, this book is ideal for cognitive scientists, philosophers of mind, neuroscientists, psychologists, researchers, academicians, and advanced-level students. The book can also help to focus the research of linguists, neurologists, and biophysicists on the biophysical basis of postulated information processing into knowledge structures. (shrink)

A sector is a basic unit of airspace whose operation is managed by air traffic controllers. The operation complexity of a sector plays an important role in air traffic management system, such as airspace reconfiguration, air traffic flow management, and allocation of air traffic controller resources. Therefore, accurate evaluation of the sector operation complexity is crucial. Considering there are numerous factors that can influence SOC, researchers have proposed several machine learning methods recently to evaluate SOC by mining the relationship (...) between factors and complexity. However, existing studies rely on hand-crafted factors, which are computationally difficult, specialized background required, and may limit the evaluation performance of the model. To overcome these problems, this paper for the first time proposes an end-to-end SOC learning framework based on deep convolutional neural network specifically for free of hand-crafted factors environment. A new data representation, i.e., multichannel traffic scenario image, is proposed to represent the overall air traffic scenario. A MTSI is generated by splitting the airspace into a two-dimension grid map and filled with navigation information. Motivated by the applications of deep learning network, the specific CNN model is introduced to automatically extract high-level traffic features from MTSIs and learn the SOC pattern. Thus, the model input is determined by combining multiple image channels composed of air traffic information, which are used to describe the traffic scenario. The model output is SOC levels for the target sector. The experimental results using a real dataset from the Guangzhou airspace sector in China show that our model can effectively extract traffic complexity information from MTSIs and achieve promising performance than traditional machine learning methods. In practice, our work can be flexibly and conveniently applied to SOC evaluation without the additional calculation of hand-crafted factors. (shrink)

To model behavioral and neural correlates of language comprehension in naturalistic environments, researchers have turned to broad‐coverage tools from natural‐language processing and machine learning. Where syntactic structure is explicitly modeled, prior work has relied predominantly on context‐free grammars (CFGs), yet such formalisms are not sufficiently expressive for human languages. Combinatory categorial grammars (CCGs) are sufficiently expressive directly compositional models of grammar with flexible constituency that affords incremental interpretation. In this work, we evaluate whether a more expressive CCG (...) provides a better model than a CFG for human neural signals collected with functional magnetic resonance imaging (fMRI) while participants listen to an audiobook story. We further test between variants of CCG that differ in how they handle optional adjuncts. These evaluations are carried out against a baseline that includes estimates of next‐word predictability from a transformer neural network language model. Such a comparison reveals unique contributions of CCG structure‐building predominantly in the left posterior temporal lobe: CCG‐derived measures offer a superior fit to neural signals compared to those derived from a CFG. These effects are spatially distinct from bilateral superior temporal effects that are unique to predictability. Neural effects for structure‐building are thus separable from predictability during naturalistic listening, and those effects are best characterized by a grammar whose expressive power is motivated on independent linguistic grounds. (shrink)

We present statistical analyses of the large‐scale structure of 3 types of semantic networks: word associations, WordNet, and Roget's Thesaurus. We show that they have a small‐world structure, characterized by sparse connectivity, short average path lengths between words, and strong local clustering. In addition, the distributions of the number of connections follow power laws that indicate a scale‐free pattern of connectivity, with most nodes having relatively few connections joined together through a small number of hubs with many connections. These (...) regularities have also been found in certain other complex natural networks, such as the World Wide Web, but they are not consistent with many conventional models of semantic organization, based on inheritance hierarchies, arbitrarily structured networks, or high‐dimensional vector spaces. We propose that these structures reflect the mechanisms by which semantic networks grow. We describe a simple model for semantic growth, in which each new word or concept is connected to an existing network by differentiating the connectivity pattern of an existing node. This model generates appropriate small‐world statistics and power‐law connectivity distributions, and it also suggests one possible mechanistic basis for the effects of learning history variables (age of acquisition, usage frequency) on behavioral performance in semantic processing tasks. (shrink)

We review some of the main implications of the free-energy principle (FEP) for the study of the self-organization of living systems – and how the FEP can help us to understand (and model) biotic self-organization across the many temporal and spatial scales over which life exists. In order to maintain its integrity as a bounded system, any biological system - from single cells to complex organisms and societies - has to limit the disorder or dispersion (i.e., the long-run (...) entropy) of its constituent states. We review how this can be achieved by living systems that minimize their variational free energy. Variational free energy is an information theoretic construct, originally introduced into theoretical neuroscience and biology to explain perception, action, and learning. It has since been extended to explain the evolution, development, form, and function of entire organisms, providing a principled model of biotic self-organization and autopoiesis. It has provided insights into biological systems across spatiotemporal scales, ranging from microscales (e.g., sub- and multicellular dynamics), to intermediate scales (e.g., groups of interacting animals and culture), through to macroscale phenomena (the evolution of entire species). A crucial corollary of the FEP is that an organism just is (i.e., embodies or entails) an implicit model of its environment. As such, organisms come to embody causal relationships of their ecological niche, which, in turn, is influenced by their resulting behaviors. Crucially, free-energy minimization can be shown to be equivalent to the maximization of Bayesian model evidence. This allows us to cast natural selection in terms of Bayesian model selection, providing a robust theoretical account of how organisms come to match or accommodate the spatiotemporal complexity of their surrounding niche. In line with the theme of this volume; namely, biological complexity and self-organization, this chapter will examine a variational approach to self-organization across multiple dynamical scales. (shrink)

Active inference offers a unified theory of perception, learning, and decision-making at computational and neural levels of description. In this article, we address the worry that active inference may be in tension with the belief–desire–intention model within folk psychology because it does not include terms for desires at the mathematical level of description. To resolve this concern, we first provide a brief review of the historical progression from predictive coding to active inference, enabling us to distinguish between active (...) inference formulations of motor control and active inference formulations of decision processes. We then show that, despite a superficial tension when viewed at the mathematical level of description, the active inference formalism contains terms that are readily identifiable as encoding both the objects of desire and the strength of desire at the psychological level of description. We demonstrate this with simple simulations of an active inference agent motivated to leave a dark room for different reasons. Despite their consistency, we further show how active inference may increase the granularity of folk-psychological descriptions by highlighting distinctions between drives to seek information versus reward—and how it may also offer more precise, quantitative folk-psychological predictions. Finally, we consider how the implicitly conative components of active inference may have partial analogues in other systems describable by the broader free energy principle to which it conforms. (shrink)

There is no shortage of pedagogical theories from the tradition formal methods of instruction to the free-play methods of unschooling. A sharp shift in education and instruction models took place with the introduction of critical pedagogy. The focus was no longer on the authority of the teacher and the submissive, passive approach taken by the learner, but rather on the engagement between the two. Still, even when critical pedagogy is utilized in a formal model of education something is (...) missing from the system—experiential learning. Although the unschooling method has been criticized it does provide the benefit of experiential learning. This paper explores the nature of education and evaluates models and theories of pedagogy with the conclusion that a paradoxical approach in which there is a merger between the formal guidelines set by traditional educational models and the experiential learning methods of unschooling approach best prepares learners for the world and to be engaged citizens. Although what, precisely, this paradoxical system would entail is not discussed in this paper, it opens the door for further discussion on the topic and for consideration of the theories which have attempted to do exactly this and improve upon them going forward. (shrink)

Similarity is one of the most important relations humans perceive, arguably subserving category learning and categorization, generalization and discrimination, judgment and decision making, and other cognitive functions. Researchers have proposed a wide range of representations and metrics that could be at play in similarity judgment, yet have not comprehensively compared the power of these representations and metrics for predicting similarity within and across different semantic categories. We performed such a comparison by pairing nine prominent vector semantic representations with seven (...) established similarity metrics that could operate on these representations, as well as supervised methods for dimensional weighting in the similarity function. This approach yields a factorial model structure with 126 distinct representation‐metric pairs, which we tested on a novel dataset of similarity judgments between pairs of cohyponymic words in eight categories. We found that cosine similarity and Pearson correlation were the overall best performing unweighted similarity functions, and that word vectors derived from free association norms often outperformed word vectors derived from text (including those specialized for similarity). Importantly, models that used human similarity judgments to learn category‐specific weights on dimensions yielded substantially better predictions than all unweighted approaches across all types of similarity functions and representations, although dimension weights did not generalize well across semantic categories, suggesting strong category context effects in similarity judgment. We discuss implications of these results for cognitive modeling and natural language processing, as well as for theories of the representations and metrics involved in similarity. (shrink)

We present statistical analyses of the large‐scale structure of 3 types of semantic networks: word associations, WordNet, and Roget's Thesaurus. We show that they have a small‐world structure, characterized by sparse connectivity, short average path lengths between words, and strong local clustering. In addition, the distributions of the number of connections follow power laws that indicate a scale‐free pattern of connectivity, with most nodes having relatively few connections joined together through a small number of hubs with many connections. These (...) regularities have also been found in certain other complex natural networks, such as the World Wide Web, but they are not consistent with many conventional models of semantic organization, based on inheritance hierarchies, arbitrarily structured networks, or high‐dimensional vector spaces. We propose that these structures reflect the mechanisms by which semantic networks grow. We describe a simple model for semantic growth, in which each new word or concept is connected to an existing network by differentiating the connectivity pattern of an existing node. This model generates appropriate small‐world statistics and power‐law connectivity distributions, and it also suggests one possible mechanistic basis for the effects of learning history variables (age of acquisition, usage frequency) on behavioral performance in semantic processing tasks. (shrink)

Biological agents can act in ways that express a sensitivity to context-dependent relevance. So far it has proven difficult to engineer this capacity for context-dependent sensitivity to relevance in artificial agents. We give this problem the label the “problem of meaning”. The problem of meaning could be circumvented if artificial intelligence researchers were to design agents based on the assumption of the continuity of life and mind. In this paper, we focus on the proposal made by enactive cognitive scientists to (...) design artificial agents that possess sensorimotor autonomy—stable, self-sustaining patterns of sensorimotor interaction that can ground values, norms and goals necessary for encountering a meaningful environment. More specifically, we consider whether the Free Energy Principle (FEP) can provide formal tools for modeling sensorimotor autonomy. There is currently no consensus on how to understand the relationship between enactive cognitive science and the FEP. However, a number of recent papers have argued that the two frameworks are fundamentally incompatible. Some argue that biological systems exhibit historical path-dependent learning that is absent from systems that minimize free energy. Others have argued that a free energy minimizing system would fail to satisfy a key condition for sensorimotor agency referred to as “interactional asymmetry”. These critics question the claim we defend in this paper that the FEP can be used to formally model autonomy and adaptivity. We will argue it is too soon to conclude that the two frameworks are incompatible. There are undeniable conceptual differences between the two frameworks but in our view each has something important and necessary to offer. The FEP needs enactive cognitive science for the solution it provides to the problem of meaning. Enactive cognitive science needs the FEP to formally model the properties it argues to be constitutive of agency. Our conclusion will be that active inference models based on the FEP provides a way by which scientists can think about how to address the problems of engineering autonomy and adaptivity in artificial agents in formal terms. In the end engaging more closely with this formalism and its further developments will benefit those working within the enactive framework. -/- . (shrink)

In this article, the author explores a model of alternative medical education being pioneered at Loyola University Chicago Stritch School of Medicine. The five-year Global Health Fieldwork Fellowship track allows two students per year to complete an extra year of medical education while living and working in a free rural clinic in the jungle lowlands of Bolivia. This alternative curricular track is unique among other existing models in that it is longitudinally immersive for at least one full additional (...) year of medical education, grounded in clinical and service learning, and heavily focused upon global health and the social components of medicine. Studies have shown that both longitudinal alternative medical curricular tracks and short-term global health electives have long-term benefits upon the professional development of participants, suggesting that the GHFF is likely to do the same. The author also argues that the GHFF is an advantageous model of global health education compared to standard offerings and provides a unique curricular model by which to foster the development of social values—such as professionalism, advocacy, and social justice—that are widely considered lacking in today’s medical education. (shrink)