Critics of the computational connectionism of the last decade suggest that it shares undesirable features with earlier empiricist or associationist approaches, and with behaviourist theories of learning. To assess the accuracy of this charge the works of earlier writers are examined for the presence of such features, and brief accounts of those found are given for Herbert Spencer, William James and the learning theorists Thorndike, Pavlov and Hull. The idea that cognition depends on associative connections among large networks of neurons (...) is indeed one with precedents, although the implications of this for psychological issues have been interpreted variously — not all versions of connectionism are alike. (shrink)

A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...) and neural models. The explanations of behavior provided are like those traditional in the physical sciences, unlike the explanations provided by symbolic models. (shrink)

This paper explores the difference between Connectionist proposals for cognitive a r c h i t e c t u r e a n d t h e s o r t s o f m o d e l s t hat have traditionally been assum e d i n c o g n i t i v e s c i e n c e . W e c l a i m t h a t t h (...) e m a j o r d i s t i n c t i o n i s t h a t , w h i l e b o t h Connectionist and Classical architectures postulate representational mental states, the latter but not the former are committed to a symbol-level of representation, or to a ‘language of thought’: i.e., to representational states that have combinatorial syntactic and semantic structure. Several arguments for combinatorial structure in mental representations are then reviewed. These include arguments based on the ‘systematicity’ of mental representation: i.e., on the fact that cognitive capacities always exhibit certain symmetries, so that the ability to entertain a given thought implies the ability to entertain thoughts with semantically related contents. We claim that such arguments make a powerful case that mind/brain architecture is not Connectionist at the cognitive level. We then consider the possibility that Connectionism may provide an account of the neural (or ‘abstract neurological’) structures in which Classical cognitive architecture is implemented. We survey a n u m b e r o f t h e s t a n d a r d a r g u m e n t s t h a t h a v e b e e n o f f e r e d i n f a v o r o f Connectionism, and conclude that they are coherent only on this interpretation. (shrink)

Physicalism is an empirical theory of the mind and its place in nature. So the physicalist must show that current neuroscience does not falsify physicalism, but instead supports it. Current neuroscience shows that a nervous system is what I call a vector function system. I provide a brief outline of the resources that empirical research has made available within the constraints of the vector function approach. Then I argue that these resources are sufficient, indeed apt, for the physicalist enterprise, by (...) offering a vector functional, hence physicalist, theory of the percept--the perceptual experience itself, a paradigm of phenomenally immediate, introspectively accessible consciousness. (shrink)

The notion of a "mental representation" is, arguably, in the first instance a theoretical construct of cognitive science. As such, it is a basic concept of the Computational Theory of Mind, according to which cognitive states and processes are constituted by the occurrence, transformation and storage (in the mind/brain) of information-bearing structures (representations) of one kind or another.

Modularity in the human brain remains a controversial issue, with disagreement over the nature of the modules that exist, and why, when, and how they emerge. It is a natural assumption that modularity offers some form of computational advantage, and hence evolution by natural selection has translated those advantages into the kind of modular neural structures familiar to cognitive scientists. However, simulations of the evolution of simplified neural systems have shown that, in many cases, it is actually non-modular architectures that (...) are most efficient. In this paper, the relevant issues are discussed and a series of simulations are presented that reveal crucial dependencies on the details of the learning algorithms and tasks that are being modelled, and the importance of taking into account known physical brain constraints, such as the degree of neural connectivity. A pattern is established which provides one explanation of why modularity should emerge reliably across a range of neural processing tasks. (shrink)

Brain functions are stochastic processes without intentionality whereas mind emerges from brain functions as a Hegelian “change from quantity”, that is, on the order of 1012 profusely interconnected neurons, “into a new quality”: the collective phenomenon of the brain's self-experience. This self-referential and self-observing quality we have in mind is capable of (recursively) observing its self-observations, i.e., interpreting change that is meaningful in relation to itself. The notion of self-interpretation embodies the idea of a “hermeneutic circle”, that is, (in interpretation (...) theory) the treatment of the whole in relation to its parts. (shrink)

Purely parallel neural networks can model object recognition in brief displays – the same conditions under which illusory conjunctions have been demonstrated empirically. Correcting errors of illusory conjunction is the “tag-assignment” problem for a purely parallel processor: the problem of assigning a spatial tag to nonspatial features, feature combinations, and objects. This problem must be solved to model human object recognition over a longer time scale. Our model simulates both the parallel processes that may underlie illusory conjunctions and the serial (...) processes that may solve the tag-assignment problem in normal perception. One component of the model extracts pooled features and another provides attentional tags that correct illusory conjunctions. Our approach addresses two questions: How can objects be identified from simultaneously attended features in a parallel, distributed representation? How can the spatial selectional requirements of such an attentional process be met by a separation of pathways for spatial and nonspatial processing? Our analysis of these questions yields a neurally plausible simulation of tag assignment based on synchronizing feature processing activity in a spatial focus of attention. (shrink)

This article argues that rapid eye movement (REM) dreaming is elaborative encoding for episodic memories. Elaborative encoding in REM can, at least partially, be understood through ancient art of memory (AAOM) principles: visualization, bizarre association, organization, narration, embodiment, and location. These principles render recent memories more distinctive through novel and meaningful association with emotionally salient, remote memories. The AAOM optimizes memory performance, suggesting that its principles may predict aspects of how episodic memory is configured in the brain. Integration and segregation (...) are fundamental organizing principles in the cerebral cortex. Episodic memory networks interconnect profusely within the cortex, creating omnidirectional “landmark” junctions. Memories may be integrated at junctions but segregated along connecting network paths that meet at junctions. Episodic junctions may be instantiated during non–rapid eye movement (NREM) sleep after hippocampal associational function during REM dreams. Hippocampal association involves relating, binding, and integrating episodic memories into a mnemonic compositional whole. This often bizarre, composite image has not been present to the senses; it is not “real” because it hyperassociates several memories. During REM sleep, on the phenomenological level, this composite image is experienced as a dream scene. A dream scene may be instantiated as omnidirectional neocortical junction and retained by the hippocampus as an index. On episodic memory retrieval, an external stimulus (or an internal representation) is matched by the hippocampus against its indices. One or more indices then reference the relevant neocortical junctions from which episodic memories can be retrieved. Episodic junctions reach a processing (rather than conscious) level during normal wake to enable retrieval. If this hypothesis is correct, the stuff of dreams is the stuff of memory. (shrink)

The general problem of visual search can be shown to be computationally intractable in a formal, complexity-theoretic sense, yet visual search is extensively involved in everyday perception, and biological systems manage to perform it remarkably well. Complexity level analysis may resolve this contradiction. Visual search can be reshaped into tractability through approximations and by optimizing the resources devoted to visual processing. Architectural constraints can be derived using the minimum cost principle to rule out a large class of potential solutions. The (...) evidence speaks strongly against bottom-up approaches to vision. In particular, the constraints suggest an attentional mechanism that exploits knowledge of the specific problem being solved. This analysis of visual search performance in terms of attentional influences on visual information processing and complexity satisfaction allows a large body of neurophysiological and psychological evidence to be tied together. (shrink)

A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...) and neural models. The explanations of behavior provided are like those traditional in the physical sciences, unlike the explanations provided by symbolic models.Higher-level analyses of these connectionist models reveal subtle relations to symbolic models. Parallel connectionist memory and linguistic processes are hypothesized to give rise to processes that are describable at a higher level as sequential rule application. At the lower level, computation has the character of massively parallel satisfaction of soft numerical constraints; at the higher level, this can lead to competence characterizable by hard rules. Performance will typically deviate from this competence since behavior is achieved not by interpreting hard rules but by satisfying soft constraints. The result is a picture in which traditional and connectionist theoretical constructs collaborate intimately to provide an understanding of cognition. (shrink)

This article describes an implemented architecture for intermediate vision. By integrating a variety of Intermediate visual mechanisms and putting them to use in support of concrete activity, the implementation demonstrates their utility. The sytem, SIVS, models psychophysical discoveries about visual attention and search. It is designed to be efficiently implementable in slow, massively parallel, locally connected hardware, such as that of the brain.SIVS addresses five fundamental problems. Visual attention is required to restrict processing to task-relevant locations in the image. Visual (...) search finds such locations. Visual routines are a means for nonuniform processing based on task demands. Intermediate objects keep track of intermediate results of this processing. Visual operators are a set of relatively abstract, general-purpose primitives for spatial analysis, out of which visual routines are assembled. (shrink)

Marr (1982) may have been one of the rst vision researchers to insist that in modeling vision it is important to separate the location of visual features from their type. He argued that in early stages of visual processing there must be “place tokens” that enable subsequent stages of the visual system to treat locations independent of what specic feature type was at that location. Thus, in certain respects a collinear array of diverse features could still be perceived as a (...) line, and under certain conditions could function as such in perceptual phenomena like the Poggendorf illusion. (shrink)