University of Southampton

Categorical Perception: Bibliography

This is the Categorical Perception bibliography (in four parts -- this is the first part). Don't worry! You are not expected to read all or even most of it, just what your group needs to prepare the subtopic you have chosen, plus a little background reading so you sample the other three subtopics too.

The full articles behind each abstract in the file you are in right now are all retrievable by clicking on the underlined portion (these are articles by me). This includes the first and last chapter of the CP book, which you should all read (whether or not you are doing CP as your project).

If you click here you will leave this file and jump instead to:

For all of the abstracts above you will unfortunately have to retrieve the full article the old way (by going to the library). (Imagine if you could get it all on the Web! Soon this will be possible; agitate for it!) For the abstracts below, however, you can get the whole article with just one more click.

See also the companion www file (1) Advanced topic summary as well as the companion file
(2) Subject-coded list for (1) a summary of the Categorical Perception segment of the Avanced Topics course and (2) a version of the bibliography coded by subject (visual, auditory, neural, etc.).


  • Harnad, S. (1987) Psychophysical and cognitive aspects of categorical perception: A critical overview. Chapter 1 of: Harnad, S. (ed.) (1987) Categorical Perception: The Groundwork of Cognition. New York: Cambridge University Press. ABSTRACT: Categorization is a very basic cognitive activity. It is involved in any task that calls for differential responding, from operant discrimination to pattern recognition to naming and describing objects and states-of-affairs. Explanations of categorization range from nativist theories denying that any nontrivial categories are acquired by learning to inductivist theories claiming that most categories are learned. "Categorical perception" (CP) is the name given to a suggestive perceptual phenomenon that may serve as a useful model for categorization in general: For certain perceptual categories, within-category differences look much smaller than between-category differences even when they are of the same size physically. For example, in color perception, differences between reds and differences between yellows look much smaller than equal-sized differences that cross the red/yellow boundary; the same is true of the phoneme categories /ba/ and /da/. Indeed, the effect of the category boundary is not merely quantitative, but qualitative.

  • Harnad, S. (1987) The induction and representation of categories. In: Harnad, S. (ed.) (1987) Categorical Perception: The Groundwork of Cognition. New York: Cambridge University Press. ABSTRACT: A provisional model is presented in which categorical perception (CP) provides our basic or elementary categories. In acquiring a category we learn to label or identify positive and negative instances from a sample of confusable alternatives. Two kinds of internal representation are built up in this learning by "acquaintance": (1) an ICONIC representation that subserves our similarity judgments and (2) an analog/digital feature-filter that picks out the invariant information allowing us to categorize the instances correctly. This second, CATEGORICAL representation is associated with the category name. Category names then serve as the atomic symbols for a third representational system, the (3) SYMBOLIC representations that underlie language and that make it possible for us to learn by "description." Connectionism is one possible mechainsm for learning the sensory invariants underlying categorization and naming. Among the implications of the model are (a) the "cognitive identity of (current) indiscriminables": Categories and their representations can only be provisional and approximate, relative to the alternatives encountered to date, rather than "exact." There is also (b) no such thing as an absolute "feature," only those features that are invariant within a particular context of confusable alternatives. Contrary to prevailing "prototype" views, however, (c) such provisionally invariant features MUST underlie successful categorization, and must be "sufficient" (at least in the "satisficing" sense) to subserve reliable performance with all-or-none, bounded categories, as in CP. Finally, the model brings out some basic limitations of the "symbol-manipulative" approach to modeling cognition, showing how (d) symbol meanings must be functionally grounded in nonsymbolic, "shape-preserving" representations -- iconic and categorical ones. Otherwise, all symbol interpretations are ungrounded and indeterminate. This amounts to a principled call for a psychophysical (rather than a neural) "bottom-up" approach to cognition.

  • Harnad, S. (1990) The Symbol Grounding Problem. Physica D 42: 335-346. ABSTRACT: There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the "symbol grounding problem": How can the semantic interpretation of a formal symbol system be made INTRINSIC to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their (arbitrary) shapes, be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: (1) "iconic representations," which are analogs of the proximal sensory projections of distal objects and events, and (2) "categorical representations," which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations," grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z"). Connectionism is one natural candidate for the mechanism that learns the invariant features underlying categorical representations, thereby connecting names to the proximal projections of the distal objects they stand for. In this way connectionism can be seen as a complementary component in a hybrid nonsymbolic/symbolic model of the mind, rather than a rival to purely symbolic modeling. Such a hybrid model would not have an autonomous symbolic "module," however; the symbolic functions would emerge as an intrinsically "dedicated" symbol system as a consequence of the bottom-up grounding of categories' names in their sensory representations. Symbol manipulation would be governed not just by the arbitrary shapes of the symbol tokens, but by the nonarbitrary shapes of the icons and category invariants in which they are grounded.

  • Harnad, S., Hanson, S.J. & Lubin, J. (1991) Categorical Perception and the Evolution of Supervised Learning in Neural Nets. In: Working Papers of the AAAI Spring Symposium on Machine Learning of Natural Language and Ontology (DW Powers & L Reeker, Eds.) pp. 65-74. Presented at Symposium on Symbol Grounding: Problems and Practice, Stanford University, March 1991; also reprinted as Document D91-09, Deutsches Forschungszentrum fur Kuenstliche Intelligenz GmbH Kaiserslautern FRG. ABSTRACT: Some of the features of animal and human categorical perception (CP) for color, pitch and speech are exhibited by neural net simulations of CP with one-dimensional inputs: When a backprop net is trained to discriminate and then categorize a set of stimuli, the second task is accomplished by "warping" the similarity space (compressing within-category distances and expanding between-category distances). This natural side-effect also occurs in humans and animals. Such CP categories, consisting of named, bounded regions of similarity space, may be the ground level out of which higher-order categories are constructed; nets are one possible candidate for the mechanism that learns the sensorimotor invariants that connect arbitrary names (elementary symbols?) to the nonarbitrary shapes of objects. This paper examines how and why such compression/expansion effects occur in neural nets.

  • Harnad, S. (1992) Connecting Object to Symbol in Modeling Cognition. In: A. Clarke and R. Lutz (Eds) Connectionism in Context Springer Verlag. ABSTRACT: Connectionism and computationalism are currently vying for hegemony in cognitive modeling. At first glance the opposition seems incoherent, because connectionism is itself computational, but the form of computationalism that has been the prime candidate for encoding the "language of thought" has been SYMBOLIC computationalism, whereas connectionism is nonsymbolic, or, as some have hopefully dubbed it, "subsymbolic"). This paper will examine what is and is not a symbol system. A hybrid nonsymbolic/symbolic system will be sketched in which the meanings of the symbols are grounded bottom-up in the system's capacity to discriminate and identify the objects they refer to. Neural nets are one possible mechanism for learning the invariants in the analog sensory projection on which successful categorization is based. "Categorical perception," in which similarity space is "warped" in the service of categorization, turns out to be exhibited by both people and nets, and may mediate the constraints exerted by the analog world of objects on the formal world of symbols.

  • Harnad, S. (1996) The Origin of Words: A Psychophysical Hypothesis. Presented at Zif Conference on Biological and Cultural Aspects of Language Development. January 20 - 22, 1992 University of Bielefeld; to appear in Durham, W & Velichkovsky B (Eds.) "Naturally Human: Origins and Destiny of Language." Muenster: Nodus Pub. ABSTRACT: It is hypothesized that words originated as the names of perceptual categories and that two forms of representation underlying perceptual categorization, iconic and categorical representations, served to GROUND a third, symbolic, form of representation. The third form of representation made it possible to name and describe our environment, chiefly in terms of categories, their memberships, and their invariant features. Symbolic representations can be shared because they are intertranslatable. Both categorization and translation are approximate rather than exact, but the approximation can be made as close as we wish. This is the central property of that universal mechanism for sharing descriptions that we call natural language.

  • Harnad, S. (1993) Grounding Symbolic Capacity in Robotic Capacity. In: Steels, L. and R. Brooks (eds.) The "artificial life" route to "artificial intelligence." Building Situated Embodied Agents. New Haven: Lawrence Erlbaum

  • Harnad, S. Hanson, S.J. & Lubin, J. (1994) Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding. In: V. Honavar & L. Uhr (eds) Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration. Academic Press. ABSTRACT: After people learn to sort objects into categories they see them differently. Members of the same category look more alike and members of different categories look more different. This phenomenon of within-category compression and between-category separation in similarity space is called categorical perception (CP). It is exhibited by human subjects, animals and neural net models. In backpropagation nets trained first to auto-associate 12 stimuli varying along a one-dimensional continuum and then to sort them into 3 categories, CP arises as a natural side-effect because of four factors: (1) Maximal interstimulus separation in hidden-unit space during auto-association learning, (2) movement toward linear separability during categorization learning, (3) inverse-distance repulsive force exerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially in interpolating CP to untrained regions of the continuum. Once similarity space has been "warped" in this way, the compressed and separated "chunks" have symbolic labels which could then be combined into symbol strings that constitute propositions about objects. The meanings of such symbolic representations would be "grounded" in the system's capacity to pick out from their sensory projections the object categories that the propositions were about.


    To return to the companion www file (1) Advanced topic summary or to the
    (2) Subject-coded list click here.

    If you click here you will leave this file and jump instead to: