Shimon Edelman

The learnability of features and their dependence on task and context do not rule out the possibility that primitives used for constructing new features are as small as pixels, nor that they are as large as object parts, or even entire objects. In fact, the simplest approach to feature acquisition may be to treat objects not as if they are composed of unknown primitives according to unknown rules, but rather as if they are what they seem: patterns of atomic features, standing in various similarity relationships to other objects, which serve as holistic features.

Beer ’s paper devotes much energy to buttressing the walls of Castle Dynamic and dredging its moat in the face of what some of its dwellers perceive as a besieging army chanting “no cognition without representation”. The divide is real, as attested by the contrast between titles such as “Intelligence without representation” and “In defense of representation”, to pick just one example from each side. It is, however, not too late for people from both sides of the moat to meet on the drawbridge and see if all that energy can be put to a better use. The parley can be organized around an attempt to identify those attributes of representations that both sides may find useful. In my view, one such attribute is the capacity for hierarchical abstraction, an aspect of the representational approach not actually mentioned by Beer. The capacity for abstraction is gained automatically by those theoretical frameworks that opt for the explanatory benefits of representation in understanding cognition. Moreover, without appropriately structured mediating states, a cognitive system would be incapable of dealing with complex reality. Thus, hierarchical abstraction is useful not just for the cognitive scientists in their attempts to scale up their understanding of cognition: it is also indispensable for cognitive systems that aspire to scale up their understanding of the world

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.

Representational systems need to use symbols as internal stand-ins for distal quantities and events. Barsalou's ideas go a long way towards making the symbol system theory of representation more appealing, by delegating one critical part of the representational burden to image-like entities. The target article, however, leaves the other critical component of any symbol system theory underspecified. We point out that the binding problem can be alleviated if a perceptual symbol system is made to rely on image-like entities not only for grounding the constituent symbols, but also for composing these into structures

The theoretical debate in linguistics during the past half-century bears an uncanny parallel to the politics of the (now defunct) Communist Bloc. The parallels are not so much in the revolutionary nature of Chomsky's ideas as in the Bolshevik manner of his takeover of linguistics (Koerner 1994) and in the Trotskyist (“permanent revolution”) flavor of the subsequent development of the doctrine of Transformational Generative Grammar (TGG) (Townsend & Bever 2001, pp. 37–40). By those standards, Jackendoff is quite a party faithful (a Khrushchev or a Dubcek, rather than a Solzhenitsyn or a Sakharov) who questions some of the components of the dogma, yet stops far short of repudiating it.

The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships. We argue that the main desiderata of a representational system — productivity and systematicity — can (indeed, for a number of reasons, should) be achieved without recourse to the classical, proposition-like compositionality. We show how this can be done, by describing a systematic and productive model of the representation of visual structure, which relies on static rather than dynamic binding and uses coarsely coded rather than atomic shape primitives.

We outline an unsupervised language acquisition algorithm and offer some psycholinguistic support for a model based on it. Our approach resembles the Construction Grammar in its general philosophy, and the Tree Adjoining Grammar in its computational characteristics. The model is trained on a corpus of transcribed child-directed speech (CHILDES). The model’s ability to process novel inputs makes it capable of taking various standard tests of English that rely on forced-choice judgment and on magnitude estimation of linguistic acceptability. We report encouraging results from several such tests, and discuss the limitations revealed by other tests in our present method of dealing with novel stimuli.

Idealized mo dels of receptive elds (RFs) can be used as building blocks for the creation of p owerful distributed computation systems. The present rep ort concentrates on inv estigating the utility of collections of RFs in representing 3D objects under changing viewing conditions. The main requirement in this task is that the pattern of activity of RFs vary as little as p ossible when the object and the camera move relative to each other. I propose a method for representing objects by RF activities, based on the observation that, in the case of rotation around a xed axis, dierences of activities of RFs that are prop erly situated with resp ect to that axis remain inv ariant. Results of computational exp eriments suggest that a representation scheme based on this algorithm for the choice of stable pairs of RFs would p erform consistently b etter than a scheme inv olving random sets of RFs. The proposed scheme may be useful under object or camera rotation, b oth for ideal Lam b ertian objects, and for real-world objects such as human faces.

Word recognition is the Petri dish of the cognitive sciences. The processes hypothesized to govern naming, identifying and evaluating words have shaped this field since its origin in the 1970s. Techniques to measure lexical processing are not just the back-bone of the typical experimental psychology laboratory, but are now routinely used by cognitive neuroscientists to study brain processing and increasingly by social and clinical psychologists (Eder, Hommel, and De Houwer 2007). Models developed to explain lexical processing have also aspired to be statements about the nature of human cognition (e.g., connectionist models, Plaut, McClelland, Seidenberg, and Patterson 1996). Words were convenient objects to study for cognitive psychologists because they are welldefined and their nature as alphabetic strings was a good fit to analysis with the computer programming languages of the 1970s and 1980s which excelled at string manipulation. But are words actually the privileged unit of mental representation and processing that all of this scientific attention makes them out to be? Like a growing number of other language researchers, our answer is no (see, e.g., (Bybee and Hopper 2001; Wray 2002). We propose that the mental representations for lexical structures form a continuum, from word combinations which have fossilized into single units (nightclub) to those that both exist as independent units and yet have bonds, varying in tightness, with the words with which they frequently co-occur (Harris 1998). The first line of support for this view is the simple observation that fluent speakers easily recognize the familiarity and cohesive quality of word combinations in their language. Examples in English include common noun compounds (last year, brand new), verb phrases (cut down, get a hold of, faced with) and other multi-word expressions such as common sayings and references to cultural concepts (saved by the bell, speed of light; Jackendoff 1995)..

Variation set structure — partial alignment of successive utterances in child-directed speech — has been shown to correlate with progress in the acquisition of syntax by children. The present study demonstrates that arranging a certain proportion of utterances in a training corpus in variation sets facilitates word segmentation and phrase structure learning in miniature artifi- cial languages by adults. Our findings have implications for understanding the mechanisms of L1 acquisition by children, and for the development of more efficient algorithms for automatic language acquisition, as well as better methods for L2 instruction.

The three commentaries of Van Orden, Spivey and Anderson, and Dietrich (with Markman’s as a backdrop) form a tableau that reminds me of a fable by Ivan Andreevich Krylov (1769 - 1844), in which a swan, a pike, and a crawfish undertake jointly to move a cart laden with goods. What transpires then is not unexpected: the swan strives skyward, the pike pulls toward the river, and the crawfish scrambles backward. The call for papers for the present ecumenically minded special issue of JETAI was designed to minimize this kind of discord, by charging the authors to examine the possibility of epistemological pluralism in cognitive science — a field whose very diversity makes fundamental disagreement more likely than in other sciences. No doubt, the road mapped out by the editor had been conceived with good intentions in mind, but where did it lead us? It has been said that no good intention must go unpunished. To celebrate this venerable academic tradition (and also because I have a reputation to maintain), the following remarks will therefore be mostly other than conciliatory; caveat lector

Lasnik’s review of the Minimalist program in syntax [1] offers cognitive scientists help in navigating some of the arcana of the current theoretical thinking in transformational generative grammar. One may observe, however, that this journey is more like a taxi ride gone bad than a free tour: it is the driver who decides on the itinerary, and questioning his choice may get you kicked out. Meanwhile, the meter in the cab of the generative theory of grammar is running, and has been since the publication of Chomsky’s Syntactic Structures in 1957. The fare that it ran up is none the less daunting for the detours made in his Aspects of Theory of Syntax in 1965, Government and Binding in 1981, and now The Minimalist Program, in 1995. Paraphrasing Winston Churchill, it seems like never in the field of cognitive science was so much owed by so many of us to so few. For most of us in the cognitive sciences this situation will appear quite benign, if we realize that it is the generative linguists who should by rights be paying this bill. The reason for that is simple and is well known in the philosophy of science: putting forward a theory is like taking out a loan, to be repayed by gleaning an empirical basis for it; theories that fail to do so are declared bankrupt. In the sciences of the mind, this maxim translates into the need to demonstrate the psychological, and, eventually, the neurobiological, reality of the theoretical constructs. Many examples of this process can be found in the study of human vision, where, as in language, direct observation of the underlying mechanisms is difficult; for instance, the concept of multiple parallel spatial frequency channels, introduced in the late 1960s, was completely vindicated by purely behavioral means over the following decade; see, e.g., [2]. In linguistics, the nature of the requisite evidence is well described by Townsend and Bever: “What do we test today if we want to explore the behavioral implications of syntax?.

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]

A metaphor that has dominated linguistics for the entire duration of its existence as a discipline views sentences as edifices consisting of Lego-like building blocks. It is assumed that each sentence is constructed (and, on the receiving end, parsed) ab novo, starting (ending) with atomic constituents, to logical semantic specifications, in a recursive process governed by a few precise algebraic rules. The assumptions underlying the Lego metaphor, as it is expressed in generative grammar theories, are: (1) perfect regularity of what Saussure called langue, (2) infinite potential recursivity of syntactic structures, (3) unlimited human capacity for linguistic creativity, (4) the impossibility of acquiring structural knowledge from examples, and (5) the impossibility of such knowledge being stored in a memory-intensive form (ensembles of exemplars).

Supposing the symbol system postulated by Barsalou is perceptual through and through -- what then? The target article outlines an intriguing and exciting theory of cognition in which (1) wellspecified, event- or object-linked percepts assume the role traditionally allotted to abstract and arbitrary symbols, and (2) perceptual simulation is substituted for processes traditionally believed to require symbol manipulation, such as deductive reasoning. We take a more extreme stance on the role of perception (in particular, vision) in shaping cognition, and propose, in addition to Barsalou's postulates, that (3) spatial frames, endowed with a perceptual structure not unlike that of the retinotopic space, pervade all sensory modalities and are used to support compositionality.

Two experiments investigated whether infants represent goal‐directed actions of others in a way that allows them to draw inferences to unobserved states of affairs (such as unseen goal states or occluded obstacles). We measured looking times to assess violation of infants' expectations upon perceiving either a change in the actions of computer‐animated figures or in the context of such actions. The first experiment tested whether infants would attribute a goal to an action that they had not seen completed. The second experiment tested whether infants would infer from an observed action the presence of an occluded object that functions as an obstacle. The looking time patterns of 12‐month‐olds indicated that they were able to make both types of inferences, while 9‐month‐olds failed in both tasks. These results demonstrate that, by the end of the first year of life, infants use the principle of rational action not only for the interpretation and prediction of goal‐directed actions, but also for making productive inferences about unseen aspects of their context. We discuss the underlying mechanisms that may be involved in the developmental change from 9 to 12 months of age in the ability to infer hypothetical (unseen) states of affairs in teleological action representations.

An image of a face depends not only on its shape, but also on the viewpoint, illumination conditions, and facial expression. A face recognition system must overcome the changes in face appearance induced by these factors. This paper investigate two related questions: the capacity of the human visual system to generalize the recognition of faces to novel images, and the level at which this generalization occurs. We approach this problems by comparing the identi cation and generalization capacity for upright and inverted faces. For upright faces, we found remarkably good generalization to novel conditions. For inverted faces, the generalization to novel views was signi cantly worse for both new illumination and viewpoint, although the performance on the training images was similar to the upright condition. Our results indicate that at least some of the processes that support generalization across viewpoint and illumination are neither universal (because subjects did not generalize as easily for inverted faces as for upright ones), nor strictly objectspeci c (because in upright faces nearly perfect generalization was possible from a single view, by itself insu cient for building a complete object-speci c model). We propose that generalization in face recognition occurs at an intermediate level that is applicable to a class of objects, and that at this level upright and inverted faces initially constitute distinct object classes.

The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships. We argue that the main desiderata of a representational system—productivity and systematicity—can (indeed, for a number of reasons, should) be achieved without recourse to the classical, proposition‐like compositionality. We show how this can be done, by describing a systematic and productive model of the representation of visual structure, which relies on static rather than dynamic binding and uses coarsely coded rather than atomic shape primitives.