In this chapter we consider unsupervised learning from two perspectives. First, we briefly look at its advantages and disadvantages as an engineering technique applied to large corpora in natural language processing. While supervised learning generally achieves greater accuracy with less data, unsupervised learning offers significant savings in the intensive labour required for annotating text. Second, we discuss the possible relevance of unsupervised learning to debates on the cognitive basis of human language acquisition. In (...) this context we explore the implications of recent work on grammar induction for poverty of stimulus arguments that purport to motivate a strong bias model of language learning, commonly formulated as a theory of Universal Grammar (UG). We examine the second issue both as a problem in computational learning theory, and with reference to empirical work on unsupervised Machine Learning (ML) of syntactic structure. We compare two models of learning theory and the place of unsupervised learning within each of them. Looking at recent work on part of speech tagging and the recognition of syntactic structure, we see how far unsupervised ML methods have come in acquiring different kinds of grammatical knowledge from raw text. (shrink)

Unsupervised learning algorithms are widely used for many important statistical tasks with numerous applications in science and industry. Yet despite their prevalence, they have attracted remarkably little philosophical scrutiny to date. This stands in stark contrast to supervised and reinforcement learning algorithms, which have been widely studied and critically evaluated, often with an emphasis on ethical concerns. In this article, I analyze three canonical unsupervised learning problems: clustering, abstraction, and generative modeling. I argue that these (...) methods raise unique epistemological and ontological questions, providing data-driven tools for discovering natural kinds and distinguishing essence from contingency. This analysis goes some way toward filling the lacuna in contemporary philosophical discourse on unsupervised learning, as well as bringing conceptual unity to a heterogeneous field more often described by what it isnot(i.e., supervised or reinforcement learning) than by what itis. I submit that unsupervised learning is not just a legitimate subject of philosophical inquiry but perhaps the most fundamental branch of all AI. However, an uncritical overreliance on unsupervised methods poses major epistemic and ethical risks. I conclude by advocating for a pragmatic, error-statistical approach that embraces the opportunities and mitigates the challenges posed by this powerful class of algorithms. (shrink)

To learn a visual code in an unsupervised manner, one may attempt to capture those features of the stimulus set that would contribute significantly to a statistically efficient representation. Paradoxically, all the candidate features in this approach need to be known before statistics over them can be computed. This paradox may be circumvented by confining the repertoire of candidate features to actual scene fragments, which resemble the “what+where” receptive fields found in the ventral visual stream in primates. We describe (...) a single-layer network that learns such fragments from unsegmented raw images of structured objects. The learning method combines fast imprinting in the feedforward stream with lateral interactions to achieve single-epoch unsupervised acquisition of spatially localized features that can support systematic treatment of structured objects [1]. (shrink)

The ability to anticipate team members' actions enables joint action towards a common goal. Task knowledge and mental simulation allow for anticipating other agents' actions and for making inferences about their underlying mental representations. In human–AI teams, providing AI agents with anticipatory mechanisms can facilitate collaboration and successful execution of joint action. This paper presents a computational cognitive model demonstrating mental simulation of operators' mental models of a situation and anticipation of their behavior. The work proposes two successive steps: (1) (...) A hierarchical cluster algorithm is applied to recognize patterns of behavior among pilots. These behavioral clusters are used to derive commonalities in situation models from empirical data (N = 13 pilots). (2) An ACT-R (adaptive control of thought - rational) cognitive model is implemented to mentally simulate different possible outcomes of action decisions and timing of a pilot. model tracing of ACT-R allows following up on operators' individual actions. Two models are implemented using the symbolic representations of ACT-R: one simulating normative behavior and the other by simulating individual differences and using subsymbolic learning. Model performance is analyzed by a comparison of both models. Results indicate the improved performance of the individual differences over the normative model and are discussed regarding implications for cognitive assistance capable of anticipating operator behavior. (shrink)

Fall detection is a challenging task that has received the attention of the research community in the recent years. This study focuses on FD using data gathered from wearable devices with tri-axial accelerometers, developing a solution centered in elderly people living autonomously. This research includes three different ways to improve a FD method: an analysis of the event detection stage, comparing several alternatives, an evaluation of features to extract for each detected event and an appraisal of up to 6 different (...) clustering scenarios to split the samples in subsets that might enhance the classification. For each clustering scenario, a specific classification stage is defined. The experimentation includes publicly available simulated fall data sets. Results show the guidelines for defining a more robust and efficient FD method for on-wrist 3DACC wearable devices. (shrink)

Unsupervised statistical learning is the standard setting for the development of the only advanced visual system that is both highly sophisticated and versatile, and extensively studied: that of monkeys and humans. In this extended abstract, we invoke philosophical observations, computational arguments, behavioral data and neurobiological findings to explain why computer vision researchers should care about (1) unsupervised learning, (2) statistical inference, and (3) the visual brain. We then outline a neuromorphic approach to structural primitive learning (...) motivated by these considerations, survey a range of neurobiological findings and behavioral data consistent with it, and conclude by mentioning some of the more challenging directions for future research. (shrink)

As it is well known, mobile phones have become a basic gadget for any individual that usually stores sensitive information. This mainly motivates the increase in the number of attacks aimed at jeopardizing smartphones, being an extreme concern above all on Android OS, which is the most popular platform in the market. Consequently, a strong effort has been devoted for mitigating mentioned incidents in recent years, even though few researchers have addressed the application of visualization techniques for the analysis of (...) malware. Within this field, the present work proposes the extension of a new technique called Hybrid Unsupervised Exploratory Plots to visualize Android malware datasets. More precisely, the novel Beta-Hebbian Learning (BHL) method is applied for the first time and validated under the frame of Hybrid Unsupervised Exploratory Plots, in conjunction with clustering methods. The informative visualization achieved provides a picture of the structure of the malware families, allowing subsequent analysis of their organization. To validate the Hybrid Unsupervised Exploratory Plot extension and its tuning, the popular Android Malware Genome dataset has been used in the experimental setting. Promising results have been obtained, suggesting that BHL applied in combination with clustering techniques in Hybrid Unsupervised Exploratory Plots are a viable resource for the visualization of malware families. (shrink)

Collaborative learning has recently achieved very significant results. It still suffers, however, from several issues, including the type of information that needs to be exchanged, the criteria for stopping and how to choose the right collaborators. We aim in this paper to improve the quality of the collaboration and to resolve these issues via a novel approach inspired by Optimal Transport theory. More specifically, the objective function for the exchange of information is based on the Wasserstein distance, with a (...) bidirectional transport of information between collaborators. This formulation allows to learns a stopping criterion and provide a criterion to choose the best collaborators. Extensive experiments are conducted on multiple data-sets to evaluate the proposed approach. (shrink)

We describe a linguistic pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of corpus data. This is achieved by compactly coding recursively structured constituent patterns, and by placing strings that have an identical backbone and similar context structure into the same equivalence class. The resulting representations constitute an efficient encoding of linguistic knowledge and support systematic generalization to unseen sentences.

Extreme Learning Machine is widely used in various fields because of its fast training and high accuracy. However, it does not primarily work well for Domain Adaptation in which there are many annotated data from auxiliary domain and few even no annotated data in target domain. In this paper, we propose a new variant of ELM called Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation for unsupervised domain adaptation. It introduces Cross-Domain Mean Approximation into the hidden layer (...) of ELM to reduce distribution discrepancy between domains for domain bias elimination, which is conducive to train a high accuracy ELM on annotated data from auxiliary domains for target tasks. Linear Discriminative Analysis is also adopted to improve the discrimination of learned model and obtain higher accuracy. Moreover, we further provide a Discriminative Kernel Extreme Learning Machine with Cross-Domain Mean Approximation as the kernelization extension of DELM-CDMA. Some experiments are performed to investigate the proposed approach, and the result shows that DELM-CDMA and DKELM-CDMA could effectively extend ELM suitable for domain adaptation and outperform ELM and many other domain adaptation approaches. (shrink)

Modeling law search and retrieval as prediction problems has recently emerged as a predominant approach in law intelligence. Focusing on the law article retrieval task, we present a deep learning framework named LamBERTa, which is designed for civil-law codes, and specifically trained on the Italian civil code. To our knowledge, this is the first study proposing an advanced approach to law article prediction for the Italian legal system based on a BERT (Bidirectional Encoder Representations from Transformers) learning framework, (...) which has recently attracted increased attention among deep learning approaches, showing outstanding effectiveness in several natural language processing and learning tasks. We define LamBERTa models by fine-tuning an Italian pre-trained BERT on the Italian civil code or its portions, for law article retrieval as a classification task. One key aspect of our LamBERTa framework is that we conceived it to address an extreme classification scenario, which is characterized by a high number of classes, the few-shot learning problem, and the lack of test query benchmarks for Italian legal prediction tasks. To solve such issues, we define different methods for the unsupervised labeling of the law articles, which can in principle be applied to any law article code system. We provide insights into the explainability and interpretability of our LamBERTa models, and we present an extensive experimental analysis over query sets of different type, for single-label as well as multi-label evaluation tasks. Empirical evidence has shown the effectiveness of LamBERTa, and also its superiority against widely used deep-learning text classifiers and a few-shot learner conceived for an attribute-aware prediction task. (shrink)

Artificial Intelligence in the form of different machine learning models is applied to Big Data as a way to turn data into valuable knowledge. The rhetoric is that ensuing predictions work well—with a high degree of autonomy and automation. We argue that we need to analyze the process of applying machine learning in depth and highlight at what point human knowledge production takes place in seemingly autonomous work. This article reintroduces classification theory as an important framework for understanding (...) such seemingly invisible knowledge production in the machine learning development and design processes. We suggest a framework for studying such classification closely tied to different steps in the work process and exemplify the framework on two experiments with machine learning applied to Facebook data from one of our labs. By doing so we demonstrate ways in which classification and potential discrimination take place in even seemingly unsupervised and autonomous models. Moving away from concepts of non-supervision and autonomy enable us to understand the underlying classificatory dispositifs in the work process and that this form of analysis constitutes a first step towards governance of artificial intelligence. (shrink)

This study investigates the types of misinformation spread on Twitter that evokes scientific authority or evidence when making false claims about the antimalarial drug hydroxychloroquine as a treatment for COVID-19. Specifically, we examined tweets generated after former U.S. President Donald Trump retweeted misinformation about the drug using an unsupervised machine learning approach called the biterm topic model that is used to cluster tweets into misinformation topics based on textual similarity. The top 10 tweets from each topic cluster were (...) content coded for three types of misinformation categories related to scientific authority: medical endorsements of hydroxychloroquine, scientific information used to support hydroxychloroquine’s use, and a comparison group that included scientific evidence opposing hydroxychloroquine’s use. Results show a much higher volume of tweets featuring medical endorsements and use of supportive scientific information compared to accurate and updated scientific evidence, that misinformation-related tweets propagated for a longer time frame, and the majority of hydroxychloroquine Twitter discourse expressed positive views about the drug. Metadata from Twitter accounts found that prominent users within misinformation discourse were more likely to have media or political affiliation and explicitly expressed support for President Trump. Conversely, prominent accounts within the scientific opposition discourse primarily consisted of medical doctors or scientists but had far less influence in the Twitter discourse. Implications of these findings and connections to related social media research are discussed, as well as cognitive mechanisms for understanding susceptibility to misinformation and strategies to combat misinformation spread via online platforms. (shrink)

The COVID-19 pandemic was a global health crisis that required US residents to understand the phenomenon, interpret the cues, and make sense within their environment. Therefore, how the communication of COVID-19 was framed to stakeholders during the early stages of the pandemic became important to guide them through specific actions in their state and subsequently with the sensemaking process. The present study examines which frames were emphasized in the states' press releases on policies and other COVID information to influence stakeholders (...) on what to focus on to help with sensemaking during the crisis. We conducted content analysis on 602 press releases from 50 US states using an unsupervised machine learning approach called Latent Dirichlet Allocation (LDA). The results show that health communication using press releases to help the public make sense of the crisis were framed to include health frames as well as economic frames. Health communication messages are typically framed with health and safety measures; however, this study shows that economic frames were emphasized more than public health frames in the government's health communication for COVID-19, which forced both large and small businesses to engage in specific socially responsible activities that were previously voluntary to support public health safety. (shrink)

The automated identification of national implementations of European directives by text similarity techniques has shown promising preliminary results. Previous works have proposed and utilized unsupervised lexical and semantic similarity techniques based on vector space models, latent semantic analysis and topic models. However, these techniques were evaluated on a small multilingual corpus of directives and NIMs. In this paper, we utilize word and paragraph embedding models learned by shallow neural networks from a multilingual legal corpus of European directives and national (...) legislation to develop unsupervised semantic similarity systems to identify transpositions. We evaluate these models and compare their results with the previous unsupervised methods on a multilingual test corpus of 43 Directives and their corresponding NIMs. We also develop supervised machine learning models to identify transpositions and compare their performance with different feature sets. (shrink)

The automated identification of national implementations of European directives by text similarity techniques has shown promising preliminary results. Previous works have proposed and utilized unsupervised lexical and semantic similarity techniques based on vector space models, latent semantic analysis and topic models. However, these techniques were evaluated on a small multilingual corpus of directives and NIMs. In this paper, we utilize word and paragraph embedding models learned by shallow neural networks from a multilingual legal corpus of European directives and national (...) legislation to develop unsupervised semantic similarity systems to identify transpositions. We evaluate these models and compare their results with the previous unsupervised methods on a multilingual test corpus of 43 Directives and their corresponding NIMs. We also develop supervised machine learning models to identify transpositions and compare their performance with different feature sets. (shrink)

In this paper we analyse the conditions for attributing to AI autonomous systems the ontological status of “artificial moral agents”, in the context of the “distributed responsibility” between humans and machines in Machine Ethics (ME). In order to address the fundamental issue in ME of the unavoidable “opacity” of their decisions with ethical/legal relevance, we start from the neuroethical evidence in cognitive science. In humans, the “transparency” and then the “ethical accountability” of their actions as responsible moral agents is not (...) in contradiction with the unavoidable “opacity” (unawareness) of the brain process by which they perform their moral judgements on the right action to execute. In fact, the moral accountability of our actions depends on what is immediately before and after our “moral judgements” on the right action to execute (formally, deontic first order logic (FOL) decisions). I.e., our moral accountability depends on the “ethical constraints” we imposed to our judgement before performing it in an opaque way. Anyway, our moral accountability depends overall on the “ethical assessment” or explicit “moral reasoning” after and over the moral judgement before executing our actions (deontic higher order logic (HOL) assessment). In this way, in the light of the AI “imitation game”, the consistent attribution of the status of ethically accountable artificial moral agents to autonomous AI systems depends on two similar conditions. Firstly, it depends on the presence of “ethical constraints” to be satisfied in their Machine Learning (ML) supervised optimization algorithm during its training phase, to give the system ethical skills (“competences”) in its decisions. Secondly – and definitely—, it depends on the presence in an AI autonomous system of a deontic HOL “ethical reasoner” to perform an automatic, and fully transparent assessment (metalogical deontic valuation) about the decisions taken by the ethically skilled ML algorithm about the right action to execute, before executing it. Finally, we show that the proper deontic FOL and HOL for this class of artificial moral agents is Kripke’s modal relational logic, in its algebraic topological formalization. This is naturally implemented in the dissipative QFT unsupervised deep learning of our brains, based on the “doubling of the degrees of freedom” (DDF), and then in the so-called “deep-belief” artificial neural networks for the statistical data pre-processing. This unsupervised learning procedure is also compliant with the usage of the “maximin fairness principle”, used as a balancing aggregation principle of the statistical variables in Sen’s formal theory of fairness. (shrink)

We describe a pattern acquisition algorithm that learns, in an unsupervised fashion, a streamlined representation of linguistic structures from a plain natural-language corpus. This paper addresses the issues of learning structured knowledge from a large-scale natural language data set, and of generalization to unseen text. The implemented algorithm represents sentences as paths on a graph whose vertices are words. Significant patterns, determined by recursive context-sensitive statistical inference, form new vertices. Linguistic constructions are represented by trees composed of significant (...) patterns and their associated equivalence classes. An input module allows the algorithm to be subjected to a standard test of English as a Second Language profi- ciency. The results are encouraging: the model attains a level of performance considered to be “intermediate” for 9th-grade students, despite having been trained on a corpus containing transcribed speech of parents directed to small children. (shrink)

We address the problem of predicting how people will spontaneously divide into groups a set of novel items. This is a process akin to perceptual organization. We therefore employ the simplicity principle from perceptual organization to propose a simplicity model of unconstrained spontaneous grouping. The simplicity model predicts that people would prefer the categories for a set of novel items that provide the simplest encoding of these items. Classification predictions are derived from the model without information either about the number (...) of categories sought or information about the distributional properties of the objects to be classified. These features of the simplicity model distinguish it from other models in unsupervised categorization (where, for example, the number of categories sought is determined via a free parameter), and we discuss how these computational differences are related to differences in modeling objectives. The predictions of the simplicity model are validated in four experiments. We also discuss the significance of simplicity in cognitive modeling more generally. (shrink)

The detection and categorization of animate motions is a crucial task underlying social interaction and perceptual decision making. Neural representations of perceived animate objects are partially located in the primate cortical region STS, which is a region that receives convergent input from intermediate-level form and motion representations. Populations of STS cells exist which are selectively responsive to specific animated motion sequences, such as walkers. It is still unclear how and to what extent form and motion information contribute to the generation (...) of such representations and what kind of mechanisms are involved in the learning processes. The article develops a cortical model architecture for the unsupervised learning of animated motion sequence representations. We demonstrate how the model automatically selects significant motion patterns as well as meaningful static form prototypes characterized by a high degree of articulation. Such key poses are selectively reinforced during learning through a cross talk between the motion and form processing streams. Furthermore, we show how sequence-selective representations are learned in STS by fusing static form and motion input from the segregated bottom-up driving input streams. Cells in STS, in turn, feed their activities recurrently to their input sites along top-down signal pathways. We show how such learned feedback connections enable predictions about future input as anticipation generated by sequence-selective STS cells. Network simulations demonstrate the computational capacity of the proposed model by reproducing several experimental findings from neurosciences and by accounting for recent behavioral data. (shrink)

Contemporary Artificial Intelligence methods, especially their subset-deep learning, are finding their way to successful implementations in the detection and classification of intrusions at the network level. This paper presents an intrusion detection mechanism that leverages Deep AutoEncoder and several Deep Decoders for unsupervised classification. This work incorporates multiple network topology setups for comparative studies. The efficiency of the proposed topologies is validated on two established benchmark datasets: UNSW-NB15 and NetML-2020. The results of their analysis are discussed in terms (...) of classification accuracy, detection rate, false-positive rate, negative predictive value, Matthews correlation coefficient and F1-score. Furthermore, comparing against the state-of-the-art methods used for network intrusion detection is also disclosed. (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)

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine, a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and (...) can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models. We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. (shrink)

We introduce a set of biologically and computationally motivated design choices for modeling the learning of language, or of other types of sequential, hierarchically structured experience and behavior, and describe an implemented system that conforms to these choices and is capable of unsupervised learning from raw natural-language corpora. Given a stream of linguistic input, our model incrementally learns a grammar that captures its statistical patterns, which can then be used to parse or generate new data. The grammar (...) constructed in this manner takes the form of a directed weighted graph, whose nodes are recursively (hierarchically) defined patterns over the elements of the input stream. We evaluated the model in seventeen experiments, grouped into five studies, which examined, respectively, (a) the generative ability of grammar learned from a corpus of natural language, (b) the characteristics of the learned representation, (c) sequence segmentation and chunking, (d) artificial grammar learning, and (e) certain types of structure dependence. The model's performance largely vindicates our design choices, suggesting that progress in modeling language acquisition can be made on a broad front—ranging from issues of generativity to the replication of human experimental findings—by bringing biological and computational considerations, as well as lessons from prior efforts, to bear on the modeling approach. (shrink)

For a robot to cohabit with people, it should be able to learn people’s nonverbal social behavior from experience. In this paper, we propose a novel machine learning method for recognizing gestures used in interaction and communication. Our method enables robots to learn gestures incrementally during human–robot interaction in an unsupervised manner. It allows the user to leave the number and types of gestures undefined prior to the learning. The proposed method (HB-SOINN) is based on a self-organizing (...) incremental neural network and the hidden Markov model. We have added an interactive learning mechanism to HB-SOINN to prevent a single cluster from running into a failure as a result of polysemy of being assigned more than one meaning. For example, a sentence: “Keep on going left slowly” has three meanings such as, “Keep on (1)”, “going left (2)”, “slowly (3)”. We experimentally tested the clustering performance of the proposed method against data obtained from measuring gestures using a motion capture device. The results show that the classification performance of HB-SOINN exceeds that of conventional clustering approaches. In addition, we have found that the interactive learning function improves the learning performance of HB-SOINN. (shrink)

We introduce a set of biologically and computationally motivated design choices for modeling the learning of language, or of other types of sequential, hierarchically structured experience and behavior, and describe an implemented system that conforms to these choices and is capable of unsupervised learning from raw natural-language corpora. Given a stream of linguistic input, our model incrementally learns a grammar that captures its statistical patterns, which can then be used to parse or generate new data. The grammar (...) constructed in this manner takes the form of a directed weighted graph, whose nodes are recursively (hierarchically) defined patterns over the elements of the input stream. We evaluated the model in seventeen experiments, grouped into five studies, which examined, respectively, (a) the generative ability of grammar learned from a corpus of natural language, (b) the characteristics of the learned representation, (c) sequence segmentation and chunking, (d) artificial grammar learning, and (e) certain types of structure dependence. The model's performance largely vindicates our design choices, suggesting that progress in modeling language acquisition can be made on a broad front—ranging from issues of generativity to the replication of human experimental findings—by bringing biological and computational considerations, as well as lessons from prior efforts, to bear on the modeling approach. (shrink)

This study investigates the performance of 21 monolingual and 56 bilingual children aged 5;6-9;0 on German-LITMUS-sentence-repetition (SRT; Hamann et al., 2013) and nonword-repetition-tasks (NWRT; Grimm et al., 2014), which were constructed according to the LITMUS-principles (Language Impairment Testing in Multilingual Settings; Armon-Lotem et al., 2015). Both tasks incorporate complex structures shown to be cross-linguistically challenging for children with Specific Language Impairment (SLI) and aim at minimizing bias against bilingual children while still being indicative of the presence of language impairment across (...) language combinations. Given the great variability in bilingual language exposure and the potential effect of language experience on language performance in bilingual children, we examined whether background variables related to bilingualism, particularly, the degree language dominance as measured by relative amount of use and exposure, could compromise the diagnostic accuracy of the German-LITMUS-SRT and NWRT. We further investigated whether a combination of the two tasks provides better diagnostic accurracy. To address this, we used an unsupervised machine learning algorithm, the Partitioning-Around-Medoids (PAM), for deriving a clinical category for the children as ±language-impaired based on performance scores on SRT and/or NWRT while withholding information about their clinical status based on standardized assessment in L1/L2. Subsequently, we calculated diagnostic accuracy and investigated which background variables (age of onset, length of exposure, degree of language-dominance, socio-economic-status, and risk factors for SLI) best explained clinical-group-membership yielded from the PAM-analysis based on NWRT and/or SRT scores. Results show that although language-dominance influences the performance of bilingual typically-developing children, especially in the SRT, the diagnostic accuracy of the tools is not compromised by language dominance: while risk factors for SLI were significant predictors for clinical group membership in all models, language dominance did not contribute at all to explaining clinical cluster membership as typically-developing or SLI based on any of the combinations of the SRT and NWRT variables. Additionally, results confirm that a combination of SRT scored by correct target structure and the structurally more complex language-dependent part of the NWRT yields better diagnostic accuracy than single measures and is only sensitive for risk factors for SLI and not to dominance levels or SES. (shrink)

Machine learning and essentialism have been connected in the past by various researchers, in order to state that the main paradigm in machine learning processes is equivalent to choosing the “essential” attributes for the machine to search for. Our goal in this paper is to show that there are connections between machine learning and essentialism, but only for some kinds of machine learning, and often not including deep learning methods. Similarity-based approaches, more connected to the (...) overall prototype theory, spanning from psychology and linguistics, seem more suited for pattern recognition and complex deep-learning issues, while for classification problems, mostly for unsupervised learning, essentialism seems like the best choice. In order to illustrate the difference better, we will connect both paths to their sources in other disciplines and see how human psychology influences our decision in machine-learning modeling as well. This leads to a philosophically very interesting consequence: even in the setting of supervised machine learning, essences are not present in data, but in targets, which in turn means that the categories which purport to be essences are in fact human-made, and hand-coded in the targets. The success of machine learning, therefore, does not give any substantial evidence for the independent existence of essential properties. Our stance here is to state that neither the existence nor the lack of “essential” properties in machine learning can lead to metaphysical, i.e., ontological claims. (shrink)

This paper investigates how unsupervised machine learning methods might make hermeneutic interpretive text analysis more objective in the social sciences. Through a close examination of the uses of topic modeling—a popular unsupervised approach in the social sciences—it argues that the primary way in which unsupervised learning supports interpretation is by allowing interpreters to discover unanticipated information in larger and more diverse corpora and by improving the transparency of the interpretive process. This view highlights that (...) class='Hi'>unsupervised modeling does not eliminate the researchers’ judgments from the process of producing evidence for social scientific theories. The paper shows this by distinguishing between two prevalent attitudes toward topic modeling, i.e., topic realism and topic instrumentalism. Under neither can modeling provide social scientific evidence without the researchers’ interpretive engagement with the original text materials. Thus the unsupervised text analysis cannot improve the objectivity of interpretation by alleviating the problem of underdetermination in interpretive debate. The paper argues that the sense in which unsupervised methods can improve objectivity is by providing researchers with the resources to justify to others that their interpretations are correct. This kind of objectivity seeks to reduce suspicions in collective debate that interpretations are the products of arbitrary processes influenced by the researchers’ idiosyncratic decisions or starting points. The paper discusses this view in relation to alternative approaches to formalizing interpretation and identifies several limitations on what unsupervised learning can be expected to achieve in terms of supporting interpretive work. (shrink)

Decisions based on algorithmic, machine learning models can be unfair, reproducing biases in historical data used to train them. While computational techniques are emerging to address aspects of these concerns through communities such as discrimination-aware data mining and fairness, accountability and transparency machine learning, their practical implementation faces real-world challenges. For legal, institutional or commercial reasons, organisations might not hold the data on sensitive attributes such as gender, ethnicity, sexuality or disability needed to diagnose and mitigate emergent indirect (...) discrimination-by-proxy, such as redlining. Such organisations might also lack the knowledge and capacity to identify and manage fairness issues that are emergent properties of complex sociotechnical systems. This paper presents and discusses three potential approaches to deal with such knowledge and information deficits in the context of fairer machine learning. Trusted third parties could selectively store data necessary for performing discrimination discovery and incorporating fairness constraints into model-building in a privacy-preserving manner. Collaborative online platforms would allow diverse organisations to record, share and access contextual and experiential knowledge to promote fairness in machine learning systems. Finally, unsupervised learning and pedagogically interpretable algorithms might allow fairness hypotheses to be built for further selective testing and exploration. Real-world fairness challenges in machine learning are not abstract, constrained optimisation problems, but are institutionally and contextually grounded. Computational fairness tools are useful, but must be researched and developed in and with the messy contexts that will shape their deployment, rather than just for imagined situations. Not doing so risks real, near-term algorithmic harm. (shrink)

We compare our model of unsupervised learning of linguistic structures, ADIOS [1], to some recent work in computational linguistics and in grammar theory. Our approach resembles the Construction Grammar in its general philosophy (e.g., in its reliance on structural generalizations rather than on syntax projected by the lexicon, as in the current generative theories), and the Tree Adjoining Grammar in its computational characteristics (e.g., in its apparent affinity with Mildly Context Sensitive Languages). The representations learned by our algorithm (...) are truly emergent from the (unannotated) corpus data, whereas those found in published works on cognitive and construction grammars and on TAGs are hand-tailored. Thus, our results complement and extend both the computational and the more linguistically oriented research into language acquisition. We conclude by suggesting how empirical and formal study of language can be best integrated. (shrink)

This paper aims to enhance security in IoT device networks through a visual tool that utilizes three projection techniques, including Beta Hebbian Learning (BHL), t-distributed Stochastic Neighbor Embedding (t-SNE) and ISOMAP, in order to facilitate the identification of network attacks by human experts. This work research begins with the creation of a testing environment with IoT devices and web clients, simulating attacks over Message Queuing Telemetry Transport (MQTT) for recording all relevant traffic information. The unsupervised algorithms chosen provide (...) a set of projections that enable human experts to visually identify most attacks in real-time, making it a powerful tool that can be implemented in IoT environments easily. (shrink)

Machine learning and statistical methods have yielded impressive results in a wide variety of natural language processing tasks. These advances have generally been regarded as engineering achievements. In fact it is possible to argue that the success of machine learning methods is significant for our understanding of the cognitive basis of language acquisition and processing. Recent work in unsupervised grammar induction is particularly relevant to this issue. It suggests that knowledge of language can be achieved through general (...) learning procedures, and that a richly articulated language faculty is not required to explain its acquisition. (shrink)

Relying on large-scale parallel corpora, neural machine translation has achieved great success in certain language pairs. However, the acquisition of high-quality parallel corpus is one of the main difficulties in machine translation research. In order to solve this problem, this paper proposes unsupervised domain adaptive neural network machine translation. This method can be trained using only two unrelated monolingual corpora and obtain a good translation result. This article first measures the matching degree of translation rules by adding relevant subject (...) information to the translation rules and dynamically calculating the similarity between each translation rule and the document to be translated during the decoding process. Secondly, through the joint training of multiple training tasks, the source language can learn useful semantic and structural information from the monolingual corpus of a third language that is not parallel to the current two languages during the process of translation into the target language. Experimental results show that better results can be obtained than traditional statistical machine translation. (shrink)

Through hypothetical scenarios, this paper analyses whether machine learning (ML) could resolve one of the main shortcomings present in Christopher Boorse’s Biostatistical Theory of health (BST). In doing so, it foregrounds the boundaries and challenges of employing ML in formulating a naturalist (i.e., prima facie value-free) definition of health. The paper argues that a sweeping dataist approach cannot fully make the BST truly naturalistic, as prior theories and values persist. It also points out that supervised learning introduces circularity, (...) rendering it incompatible with a naturalistic perspective. Additionally, it underscores the need for pre-existing auxiliary theories to assess results from unsupervised learning. It emphasizes the importance of understanding the epistemological entanglements between data and data processing methods to manage expectations about what data patterns can predict. In conclusion, the paper argues against delegating the final authority for defining complex concepts like health to AI systems, as it necessitates ethical judgment and capacities for deliberation that AI currently lacks. It also warns against granting creators and deployers of AI systems the discretionary authority to determine these definitions outside the wider social discussion, advocating for ongoing public engagement on normative notions. Failure to do so risks limiting individuals and collectives’ ability to shape a just digital future and diminishes their fundamental epistemic agency. (shrink)