Analogical cognition refers to the ability to detect, process, and learn from relational similarities. The study of analogical and similarity cognition is widely considered one of the ‘success stories’ of cognitive science, exhibiting convergence across many disciplines on foundational questions. Given the centrality of analogy to mind and knowledge, it would benefit philosophers investigating topics in epistemology and the philosophies of mind and language to become familiar with empirical models of analogical cognition. The goal of this essay (...) is to describe recent empirical work on analogical cognition as well as model applications to philosophical topics. Topics to be discussed include the epistemological distinction between implicit knowledge and explicit knowledge, the debate between empiricists and nativists, the frame problem, expertise, creativity and autism, cognitive architecture, and relational knowledge. Particular attention is given to Dedre Gentner and colleague’s structure-mapping theory – the most developed and widely accepted model of analogical cognition. (shrink)
Learning from examples is a very effective means of initial cognitive skill acquisition. There is an enormous body of research on the specifics of this learning method. This article presents an instructionally oriented theory of example-based learning that integrates theoretical assumptions and findings from three research areas: learning from worked examples, observational learning, and analogical reasoning. This theory has descriptive and prescriptive elements. The descriptive subtheory deals with (a) the relevance and effectiveness of examples, (...) (b) phases of skill acquisition, and (c) learning processes. The prescriptive subtheory proposes instructional principles that make full exploitation of the potential of example-based learning possible. (shrink)
Human cognition is striking in its brilliance and its adaptability. How do we get that way? How do we move from the nearly helpless state of infants to the cognitive proficiency that characterizes adults? In this paper I argue, first, that analogical ability is the key factor in our prodigious capacity, and, second, that possession of a symbol system is crucial to the full expression of analogical ability.
The theory of mind debate has reached a “hybrid consensus” concerning the status of theory-theory and simulation-theory. Extant hybrid models either specify co-dependency and implementation relations, or distribute mentalizing tasks according to folk-psychological categories. By relying on a non-developmental framework these models fail to capture the central connection between simulation and theory. I propose a “dynamic” hybrid that is informed by recent work on the nature of similarity cognition. I claim that Gentner’s model of structure-mapping allows us to understand simulation (...) as a process in which psychological representations are aligned, causing the spontaneous abstraction of theoretical generalizations about the psychological domain. (shrink)
Adult humans show exceptional relational ability relative to other species. In this research, we trace the development of this ability in young children. We used a task widely used in comparative research—the relational match-to-sample task, which requires participants to notice and match the identity relation: for example, AA should match BB instead of CD. Despite the simplicity of this relation, children under 4 years of age failed to pass this test (Experiment 1), and their performance did not improve even with (...) initial feedback (Experiment 2). In Experiments 3 and 4, we found that two kinds of symbolic-linguistic experience can facilitate relational reasoning in young children. Our findings suggest that children learn to become adept analogical thinkers, and that language fosters this learning in at least two distinct ways. (shrink)
Reflection is today a watchword in many learning contexts. Experience is said to be transformed to knowledge when we reflect on it, university students are expected to acquire the ability to reflect critically, and we want practitioners to be reflective practitioners in order to improve their professional practice. If we consider what people mean when they talk about reflection in practice, we will discover that they often mean different things. Moreover, their conceptions of reflection are guided by images rather (...) than by definitions. This paper explores six distinct images of reflection and discusses the consequences of adopting one or more of these images in learning situations: (1) dedoublement, (2) analogical thinking, (3) mirror, (4) experiment, (5) puzzle solving, (6) criss-crossing a landscape. Reflective thinking can be improved if we are sensible of what we are reflecting about and according to which image of reflection we are doing it, since the step between using an image and seeing this image as a model is short. Using models, in turn, implies knowing their limits. (shrink)
The purpose of this chapter is to outline some of the thinking behind new e-learning technology, including e-portfolios and personal learning environments. Part of this thinking is centered around the theory of connectivism, which asserts that knowledge - and therefore the learning of knowledge - is distributive, that is, not located in any given place (and therefore not 'transferred' or 'transacted' per se) but rather consists of the network of connections formed from experience and interactions with a (...) knowing community. And another part of this thinking is centered around the new, and the newly empowered, learner, the member of the net generation, who is thinking and interacting in new ways. These trends combine to form what is sometimes called 'e-learning 2.0' - an approach to learning that is based on conversation and interaction, on sharing, creation and participation, on learning not as a separate activity, but rather, as embedded in meaningful activities such as games or workflows. (shrink)
We consider several ways in which a good understanding of modern techniques and principles in physics can elucidate ecology. We focus on analogical reasoning between these two branches of science. This style of reasoning requires an understanding of both sciences and an appreciation of the similarities and points of contact between the two. In the current ecological literature on the relationship between ecology and physics, there has been some misunderstanding about the nature of modern physics and its methods. Physics (...) is seen as being much cleaner and tidier than ecology. When ecology is compared to this idealised, fictional version of physics, ecology looks very different, and the prospect of ecology and physics learning from one another is questionable. We argue that physics, once properly appreciated, is more like ecology than ecologists have thus far appreciated. Physicists and ecologists can and do learn from each other, and in this paper we outline how analogical reasoning can facilitate such exchanges. (shrink)
Analogical transfer in sequence learning is presented as an example of how the type-2 problem of learning an unbounded number of isomorphic sequences is reduced to the type-1 problem of learning a small finite set of sequences. The commentary illustrates how the difficult problem of appropriate analogical filter creation and selection is addressed while avoiding the trap of strong nativism, and it provides theoretical and experimental evidence for the existence of dissociable mechanisms for type-1 (...) class='Hi'>learning and type-2 recoding. (shrink)
We present a PDP model of binary choice verbal analogy problems (A:B as C:[D1|D2], where D1 and D2 represent choice alternatives). We train a recurrent neural network in item-relation- item triples and use this network to test performance on analogy questions. Without training on analogy problems per se, the model explains the developmental shift from associative to relational responding as an emergent consequence of learning upon the environment’s statistics. Such learning allows gradual, item-specific acquisition of relational knowledge to (...) overcome the influence of unbalanced association frequency, accounting for association effects of analogical reasoning seen in cognitive development. The network also captures the overall degradation in performance after anterior temporal damage by deleting a fraction of learned connections, while capturing the return of associative dominance after frontal damage by treating frontal structures as necessary for maintaining activation of A and B while seeking a relation between C and D. While our theory is still far from being complete it provides a unified explanation of findings that need to be considered together in any integrated account of analogical reasoning. (shrink)
In this new volume in the Oxford Psychology Series, the author presents a highly readable account of the cognitive unconscious, focusing in particular on the problem of implicit learning. Implicit learning is defined as the acquisition of knowledge that takes place independently of the conscious attempts to learn and largely in the absence of explicit knowledge about what was acquired. One of the core assumptions of this argument is that implicit learning is a fundamental, "root" process, one (...) that lies at the very heart of the adaptive behavioral repertoire of every complex organism. The author's goals are to outline the essential features of implicit learning that have emerged from the many studies that have been carried out in a variety of experimental laboratories over the past several decades; to present the various alternative perspectives on this issue that have been proposed by other researchers and to try to accommodate these views with his own; to structure the literature so that it can be seen in the context of standard heuristics of evolutionary biology; to present the material within a functionalist approach and to try to show why the experimental data should be seen as entailing particular epistemological perspectives; and to present implicit processing as encompassing a general and ubiquitous set of operations that have wide currency and several possible applications. Chapter 1 begins with the core problem under consideration in this book, a characterization of "implicit learning" as it has come to be used in the literature. Reber puts this seemingly specialized topic into a general framework and suggests a theoretical model based on standard heuristics of evolutionary biology. In his account, Reber weaves a capsule history of interest in and work on the cognitive unconscious. Chapter 2 turns to a detailed overview of the experimental work on the acquisition of implicit knowledge, which currently is of great interest. Chapter 3 develops the evolutionary model within which one can see learning and cognition as richly intertwining issues and not as two distinct fields with one dominating the other. Finally, Chapter 4 explores a variety of entailments and speculations concerning implicit cognitive processes and their general role in the larger scope of human performance. (shrink)
Christopher Winch launches a vigorous Wittgensteinian attack on both the "romantic" Rousseauian and the "scientific" cognitivist traditions in learning theory. These two schools, he argues, are more closely related than is commonly realized.
The achievement of intentional learning is a powerful paradigm for the objectives and methods of the teaching of philosophy. This paradigm sees the objectives and methods of such teaching as based not simply on the mastery of content, but as rooted in attempts to shape the various affective and cognitive factors that influence students’ learning efforts. The goal of such pedagogy is to foster an intentional learning orientation, one characterized by self-awareness, active monitoring of the learning (...) process, and a desire for publicly certified expertise. I provide a number of examples of philosophy-specific teaching strategies that follow this paradigm. (shrink)
This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: Can perceptual experience be modified by reason?
This report highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York on March 19th and 20th, 2012: 1. What is perceptual learning? 2. Can perceptual experience be modified by reason? 3. How does perceptual learning alter perceptual phenomenology? 4. How does perceptual learning alter the contents of perception? 5. How is perceptual learning coordinated with action?
This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: What counts as cognitive penetration?
Learning is a changing phenomenon, depending on the advances in theory and research. This book presents a relatively new approach to learning, based on meaningful human activities in cultural practices and in collaboration with others. It draws extensively from the ideas of Lev Vygotsky and his recent followers. The book presents ideas that elaborate this learning theory and also gives recent developments and applications of this approach in a variety of educational situations in and outside of school. (...) A core issue in the research presented in this book consists of the way people learn to make sense of and give meaning to cultural instruments and practices in collaboration with others. (shrink)
Jerry Fodor's argument for an innate language of thought continues to be a hurdle for researchers arguing that natural languages provide us with richer conceptual systems than our innate cognitive resources. I argue that because the logical/formal terms of natural languages are given a usetheory of meaning, unlike predicates, logical/formal terms might be learned without a mediating internal representation. In that case, our innate representational system might have less logical structure than a natural language, making it possible that we augment (...) our innate representational system and improve our ability to think by learning a natural language. (shrink)
Since educators are always looking for ways to improve their practice, and since empirical science is now accepted in our worldview as the final arbiter of truth, it is no surprise they have been lured toward cognitive neuroscience in hopes that discovering how the brain learns will provide a nutshell explanation for student learning in general. I argue that identifying the person with the brain is scientism (not science), that the brain is not the person, and that it is (...) the person who learns. In fact the brain only responds to the learning of embodied experience within the extra-neural network of intersubjective communications. Learning is a dynamic, cultural activity, not a neural program. Brain-based learning is unnecessary for educators and may be dangerous in that a culturally narrow ontology is taken for granted, thus restricting our creativity and imagination, and narrowing the human community. (shrink)
In this article I challenge the widely held assumption that human culture is inherited by means of social learning. First, I address the distinction between “social” learning and “individual” learning. I argue that most cultural ideas are not acquired by one form of learning or the other, but from a hybrid of both. Second, I discuss how individual learning can interact with niche construction. I argue that these processes collectively provide a non-social route for learned (...) ideas to be inherited and cumulatively modified. I conclude that human culture is not inherited by social learning alone; the capacities to learn from and modify our environments also play a significant role. (shrink)
This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: What is perceptual learning?
This report highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012: 1. How should we demarcate perceptual learning from perceptual development? 2. What are the origins of multimodal associations? 3. Does our representation of time provide an amodal framework for multi-sensory integration? 4. What counts as cognitive penetration? 5. How can philosophers and psychologists most fruitfully collaborate?
Two great problems of learning confront humanity: learning about the universe, and learning how to live wisely. The first problem was solved with the creation of modern science, but the second problem has not been solved. This combination puts humanity into a situation of unprecedented danger. In order to solve the second problem we need to learn from our solution to the first problem. This requires that we bring about a revolution in the overall aims and methods (...) of academic inquiry, so that it takes up its proper task of promoting wisdom. (shrink)
In response to the difficulty of teaching an increasingly large number of students who are ill prepared for the sort of abstract thinking and well-structured essay writing that are essential to the field of Philosophy, I have discovered a five-step method for teaching students in my Philosophy and Social Ethics course how to examine any ethical issue and write well-structured essays discussing the issue. Just as important, students are now required to take more responsibility for the learning process which, (...) I believe, is an appropriate goal for a course in Ethics. (shrink)
Questions about learning and discovery have fascinated philosophers from Plato onwards. Does the mind bring innate resources of its own to the process of learning or does it rely wholly upon experience? Plato was the first philosopher to give an innatist response to this question and in doing so was to provoke the other major philosophers of ancient Greece to give their own rival explanations of learning. This book is the first to examine these theories of (...) class='Hi'>learning in relation to each other. It presents an entirely new interpretation of the theory of recollection which also changes the way we understand the development of ancient philosophy after Plato. The final section of the book compares ancient theories of learning with the seventeenth-century debate about innate ideas, and finds that the relation between the two periods is far more interesting and complete than is usually supposed. (shrink)
Nelson Goodman’s new riddle of induction forcefully illustrates a challenge that must be confronted by any adequate theory of inductive inference: provide some basis for choosing among alternative hypotheses that fit past data but make divergent predictions. One response to this challenge is to distinguish among alternatives by means of some epistemically significant characteristic beyond fit with the data. Statistical learning theory takes this approach by showing how a concept similar to Popper’s notion of degrees of testability is linked (...) to minimizing expected predictive error. In contrast, formal learning theory appeals to Ockham’s razor, which it justifies by reference to the goal of enhancing efficient convergence to the truth. In this essay, I show that, despite their differences, statistical and formal learning theory yield precisely the same result for a class of inductive problems that I call strongly VC ordered , of which Goodman’s riddle is just one example. (shrink)
This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How does perceptual learning alter perceptual phenomenology?
This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How is perceptual learning coordinated with action?
The purpose of professional education programs is to prepare aspiring professionals for the challenges of practice within a particular profession. These programs typically seek to ensure the acquisition of necessary knowledge and skills, as well as providing opportunities for their application. While not denying the importance of knowledge and skills, this paper reconfigures professional education as a process of becoming. Learning to become a professional involves not only what we know and can do, but also who we are (becoming). (...) It involves integration of knowing, acting, and being in the form of professional ways of being that unfold over time. When a professional education program focuses on the acquisition and application of knowledge and skills, it falls short of facilitating their integration into professional ways of being. In addition, through such a focus on epistemology (or theory of knowing), ontology (or theory of being) is overlooked. This paper explores what it means to develop professional ways of being where the focus is becoming, not simply knowing as an end in itself. (shrink)
This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: How can philosophers and psychologists most fruitfully collaborate?
Dialogue is a seminal concept within the work of the Brazilian adult education theorist, Paulo Freire, and the Russian literary critic and philosopher, Mikhail Bakhtin. While there are commonalities in their understanding of dialogue, they differ in their treatment of dialectic. This paper addresses commonalities and dissonances within a Bakhtin-Freire dialogue on the notions of dialogue and dialectic. It then teases out some of the implications for education theory and practice in relation to two South African contexts of learning (...) that facilitate the access to education of disadvantaged groups, one in higher education and the other in early childhood education. (shrink)
This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: Does our representation of time provide and amodal framework for multi-sensory integration?
This is an excerpt of a report that highlights and explores five questions that arose from the Network for Sensory Research workshop on perceptual learning and perceptual recognition at the University of York in March, 2012. This portion of the report explores the question: How does perceptual learning alter the contents of perception?
Social reporting has become an increasingly important dimension of the corporate social responsibility process. The growing necessity to include the social dimension in reporting practices raises important questions about the nature of social responsibility and its impact on corporate and individual behaviour and performance. The literature has yet to provide a reliable theoretical definition of corporate social responsibility and performance, however. Based on the approach proposed by Simons, we argue that organisational reporting about social responsibility can be viewed as a (...)learning tool in some instances. Under this view the design and implementation of corporate social reporting procedures may lead to individual and organisational dynamic changes that foster organisational performance. Research propositions are then derived from the analysis. (shrink)
The recent corporate scandals in the United States have caused a renewed interest and focus on teaching business ethics. Business schools and their faculties are reexamining the teaching of business ethics and are reassessing their responsibilities to produce honest and truthful managers who live lives of integrity and ethical accountability. The authors recognize that no agreement exists among business schools and their faculties regarding what should be the content and pedagogy of a course in business ethics. However, the authors hold (...) that regardless of one’s biases regarding the content and pedagogy, the effective teaching of business ethics requires that the instructor in designing and delivering a business ethics course needs to focus particular attention on four principal questions: (1) what are the objectives or targeted learning outcomes of the course? (2) what kind of learning environment should be created? (3) what learning processes need to be employed to achieve the goals? and (4) what are the roles of the participants in the learning experience? The answers to these questions provide the foundations for any business ethics course. The answers are major determinants of the impact of a business ethics course on the thinking of students and the views on the ethical and professional accountabilities and responsibilities of managers in the workplace. (shrink)
This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: How should we demarcate perceptual learning from perceptual development?
This is an excerpt from a report that highlights and explores five questions which arose from the workshop on perceptual learning and perceptual recognition at the University of Toronto, Mississauga on May 10th and 11th, 2012. This excerpt explores the question: What are the origins of multimodal associations?
This paper discusses the possibility of modelling inductive inference (Gold 1967) in dynamic epistemic logic (see e.g. van Ditmarsch et al. 2007). The general purpose is to propose a semantic basis for designing a modal logic for learning in the limit. First, we analyze a variety of epistemological notions involved in identification in the limit and match it with traditional epistemic and doxastic logic approaches. Then, we provide a comparison of learning by erasing (Lange et al. 1996) and (...) iterated epistemic update (Baltag and Moss 2004) as analyzed in dynamic epistemic logic. We show that finite identification can be modelled in dynamic epistemic logic, and that the elimination process of learning by erasing can be seen as iterated belief-revision modelled in dynamic doxastic logic. Finally, we propose viewing hypothesis spaces as temporal frames and discuss possible advantages of that perspective. (shrink)
The paper uses ideas from Machine Learning, Artificial Intelligence and Genetic Algorithms to provide a model of the development of a fight-or-flight response in a simulated agent. The modelled development process involves (simulated) processes of evolution, learning and representation development. The main value of the model is that it provides an illustration of how simple learning processes may lead to the formation of structures which can be given a representational interpretation. It also shows how these may form (...) the infrastructure for closely-coupled agent/environment interaction. (shrink)
Understanding causal structure is a central task of human cognition. Causal learning underpins the development of our concepts and categories, our intuitive theories, and our capacities for planning, imagination and inference. During the last few years, there has been an interdisciplinary revolution in our understanding of learning and reasoning: Researchers in philosophy, psychology, and computation have discovered new mechanisms for learning the causal structure of the world. This new work provides a rigorous, formal basis for theory theories (...) of concepts and cognitive development, and moreover, the causal learning mechanisms it has uncovered go dramatically beyond the traditional mechanisms of both nativist theories, such as modularity theories, and empiricist ones, such as association or connectionism. (shrink)
This article provides the foundation for a new predictive theory of animal learning that is based upon a simple logical model. The knowledge of experimental subjects at a given time is described using logical equations. These logical equations are then used to predict a subject’s response when presented with a known or a previously unknown situation. This new theory suc- cessfully anticipates phenomena that existing theories predict, as well as phenomena that they cannot. It provides a theoretical account for (...) phenomena that are beyond the domain of existing models, such as extinction and the detection of novelty, from which “external inhibition” can be explained. Examples of the methods applied to make predictions are given using previously published results. The present theory proposes a new way to envision the minimal functions of the nervous system, and provides possible new insights into the way that brains ultimately create and use knowledge about the world. (shrink)
Implicit Learning and Consciousness challenges conventional wisdom and presents the most up-to-date studies to define, quantify and test the predictions of the main models of implicit learning. The chapters include a variety of research from computer modeling, experimental psychology and neural imaging to the clinical data resulting from work with amnesics. The result is a topical book that provides an overview of the debate on implicit learning, and the various philosophical, psychological and neurological frameworks in which it (...) can be placed. It will be of interest to undergraduates, postgraduates and the philosophical, psychological and modeling research community. (shrink)
We evaluate the asymptotic performance of boundedly-rational strategies in multi-armed bandit problems, where performance is measured in terms of the tendency (in the limit) to play optimal actions in either (i) isolation or (ii) networks of other learners. We show that, for many strategies commonly employed in economics, psychology, and machine learning, performance in isolation and performance in networks are essentially unrelated. Our results suggest that the appropriateness of various, common boundedly-rational strategies depends crucially upon the social context (if (...) any) in which such strategies are to be employed. (shrink)
In the current socio-political climate pedagogies consistent with rationalism are in the ascendancy. One way to challenge the purchase of rationalism within educational discourse and practice is through the body, or by re-thinking the nature of mind-body relations. While the orientation of this paper is ultimately phenomenological, it takes as its point of departure recent feminist scholarship, which is demonstrating that attending to physiology can provide insight into the complexity of mind-body relations. Elizabeth Wilson's account of the role of the (...) gut in psychological processes suggests a far less hierarchical relation between brain and body than rationalism allows. Such insights are also supported by recent phenomenological inquiries into cognition and the body. My question is, what implications do these insights have for how the nature of embodiment is understood, and, by extension, learning? This paper explores how informal, non-cognitive modes of knowing, or of engaging with the world, inform learning in higher education contexts. More specifically, it raises the question of what role non-cognitive modes of engagement, such as sensibility, have in augmenting, enabling or delimiting the learning process. (shrink)
Design research has been positioned as an important methodological contribution of the learning sciences. Despite the publication of a handbook on the subject, the practice of design research in education remains an eclectic collection of specific approaches implemented by different researchers and research groups. In this paper, I examine the learning sciences as a design science to identify its fundamental goals, methods, affiliations, and assumptions. I argue that inherent tensions arise when attempting to practice design research as an (...) analytic science. Drawing inspiration and insight from Chinese philosophy and the practice of Chinese medicine, I propose that the learning sciences may better attain its claims to science through greater reliance on inductive synthesis rather than linear causal analysis. In so doing, I reposition the endeavor of science making within the metaphysics of process philosophy instead of classical Western philosophy. I suggest that theory building will be strengthened empirically and pragmatically by more careful observation and systematic generalization of the stability patterns of design related phenomena. It also needs to be more situated in its orientation. (shrink)
Fodor's and Pylyshyn's stand on systematicity in thought and language has been debated and criticized. Van Gelder and Niklasson, among others, have argued that Fodor and Pylyshyn offer no precise definition of systematicity. However, our concern here is with a learning based formulation of that concept. In particular, Hadley has proposed that a network exhibits strong semantic systematicity when, as a result of training, it can assign appropriate meaning representations to novel sentences (both simple and embedded) which contain words (...) in syntactic positions they did not occupy during training. The experience of researchers indicates that strong systematicity in any form is difficult to achieve in connectionist systems.Herein we describe a network which displays strong semantic systematicity in response to Hebbian, connectionist training. During training, two-thirds of all nouns are presented only in a single syntactic position (either as grammatical subject or object). Yet, during testing, the network correctly interprets thousands of sentences containing those nouns in novel positions. In addition, the network generalizes to novel levels of embedding. Successful training requires a, corpus of about 1000 sentences, and network training is quite rapid. The architecture and learning algorithms are purely connectionist, but classical insights are discernible in one respect, viz, that complex semantic representations spatially contain their semantic constituents. However, in other important respects, the architecture is distinctly non-classical. (shrink)