This paper critically examines the claim that parallel distributed processing (PDP) networks are autonomous learning systems. A PDP model of a simple distributed associative memory is considered. It is shown that the 'generic' PDP architecture cannot implement the computations required by this memory system without the aid of external control. In other words, the model is not autonomous. Two specific problems are highlighted: (i) simultaneous learning and recall are not permitted to occur as would be required of an autonomous system; (...) (ii) connections between processing units cannot simultaneously represent current and previous network activation as would be required if learning is to occur. Similar problems exist for more sophisticated networks constructed from the generic PDP architecture. We argue that this is because these models are not adequately constrained by the properties of the functional architecture assumed by PDP modelers. It is also argued that without such constraints, PDP researchers cannot claim to have developed an architecture radically different from that proposed by the Classical approach in cognitive science. (shrink)

PDP networks that use nonmonotonic activation functions often produce hidden unit regularities that permit the internal structure of these networks to be interpreted (Berkeley et al., 1995; McCaughan, 1997; Dawson, 1998). In particular, when the responses of hidden units to a set of patterns are graphed using jittered density plots, these plots organize themselves into a set of discrete stripes or bands. In some cases, each band is associated with a local interpretation. On the basis of these observations, Berkeley (2000) (...) has suggested that these bands are both subsymbolic and symbolic in nature, and has used the analysis of one network to support the claim that there are fewer differences between symbols and subsymbols than one might expect. We suggest below that this conclusion is premature. First, in many cases the local interpretation of each band is difficult to relate to the interpretation of a network's response; a more appropriate relationship only emerges when a band associated with one hidden unit is considered in the context of other bands associated with other hidden units (i.e., interpretations of distributed representations are more useful than interpretations of local representations). Second, the content that a band designates to an external observer (i.e., the interpretation assigned to a band by the researcher) can be quite different from the content that a band designates to the output units of the network itself.. We use two different network simulations – including the one described by Berkeley (2000) – to illustrate these points. We conclude that current evidence involving interpretations of nonmonotonic PDP networks actually illustrates the differences between symbolic and subsymbolic processing. (shrink)

There is widespread belief that connectionist networks are dramatically different from classical or symbolic models. However, connectionists rarely test this belief by interpreting the internal structure of their nets. A new approach to interpreting networks was recently introduced by Berkeley et al. (1995). The current paper examines two implications of applying this method: (1) that the internal structure of a connectionist network can have a very classical appearance, and (2) that this interpretation can provide a cognitive theory that cannot be (...) dismissed as a mere implementation. (shrink)

One new tradition that has emerged from early research on autonomous robots is embodied cognitive science. This paper describes the relationship between embodied cognitive science and a related tradition, synthetic psychology. It is argued that while both are synthetic, embodied cognitive science is antirepresentational while synthetic psychology still appeals to representations. It is further argued that modern connectionism offers a medium for conducting synthetic psychology, provided that researchers analyze the internal representations that their networks develop. The paper then provides a (...) detailed example of the synthetic approach by showing how the construction (and subsequent analysis) of a connectionist network can be used to contribute to a theory of how humans solve Piaget's classic balance scale task. (shrink)

A number of studies in the apparent motion literature were examined using the cognitive penetrability criterion to determine the extent to which beliefs affect the perception of apparent motion. It was found that the interaction between the perceptual processes mediating apparent motion and higher order processes appears to be limited. In addition, perceptual and inferential beliefs appear to have different effects on perceived motion optimality and direction. Our findings suggest that the system underlying apparent motion perception has more than one (...) stage and is informationally encapsulated from cognitive factors. (shrink)

One new tradition that has emerged from early research on autonomous robots is embodied cognitive science. This paper describes the relationship between embodied cognitive science and a related tradition, synthetic psychology. It is argued that while both are synthetic, embodied cognitive science is antirepresentational while synthetic psychology still appeals to representations. It is further argued that modern connectionism offers a medium for conducting synthetic psychology, provided that researchers analyze the internal representations that their networks develop. The paper then provides a (...) detailed example of the synthetic approach by showing how the construction of a connectionist network can be used to contribute to a theory of how humans solve Piaget's classic balance scale task. (shrink)

How might artificial neural networks (ANNs) inform cognitive science? Often cognitive scientists use ANNs but do not examine their internal structures. In this paper, we use ANNs to explore how cognition might represent musical properties. We train ANNs to classify musical chords, and we interpret network structure to determine what representations ANNs discover and use. We find connection weights between input units and hidden units can be described using Fourier phase spaces, a representation studied in musical set theory. We find (...) the total signal coming through these weighted connection weights is a measure of the similarity between two Fourier structures: the structure of the hidden unit's weights and the structure of the stimulus. This is surprising because neither of these Fourier structures is computed by the hidden unit. We then show how output units use such similarity measures to classify chords. However, we also find different types of units—units that use different activation functions—use this similarity measure very differently. This result, combined with other findings, indicates that while our networks are related to the Fourier analysis of musical sets, they do not perform Fourier analyses of the kind usually described in musical set theory. Our results show Fourier representations of music are not limited to musical set theory. Our results also suggest how cognitive psychologists might explore Fourier representations in musical cognition. Critically, such theoretical and empirical implications require researchers to understand how network structure converts stimuli into responses. (shrink)

Pylyshyn argues that many of the methods used to study perception are too coarse to detect the distinction between perceptual and cognitive processing. We suggest that the reason for this is that the theories used to guide research in perception are at fault. More powerful theories – for instance, computer simulations – will be required to identify where perception ends and where cognition begins.

Schyns et al.'s (1998) target article raises a conflict between the need for a fixed functional architecture in an explanatory cognitive science and the need for a system to learn to detect new features. This conflict can be resolved by avoiding the scope slip in which properties of objects are erroneously viewed as being properties of their representations.