This paper examines whether a classical model could be translated into a PDP network using a standard connectionist training technique called extra output learning. In Study 1, standard machine learning techniques were used to create a decision tree that could be used to classify 8124 different mushrooms as being edible or poisonous on the basis of 21 different Features (Schlimmer, 1987). In Study 2, extra output learning was used to insert this decision tree into a PDP network being trained on (...) the identical problem. An interpretation of the trained network revealed a perfect mapping from its internal structure to the decision tree, representing a precise translation of the classical theory to the connectionist model. In Study 3, a second network was trained on the mushroom problem without using extra output learning. An interpretation of this second network revealed a different algorithm for solving the mushroom problem, demonstrating that the Study 2 network was indeed a proper theory translation. (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)

Connectionist research first emerged in the 1940s. The first phase of connectionism attracted a certain amount of media attention, but scant philosophical interest. The phase came to an abrupt halt, due to the efforts of Minsky and Papert (1969), when they argued for the intrinsic limitations of the approach. In the mid-1980s connectionism saw a resurgence. This marked the beginning of the second phase of connectionist research. This phase did attract considerable philosophical attention. It was of philosophical interest, as it (...) offered a way of counteracting the conceptual ties to the philosophical traditions of atomism, rationalism, logic, nativism, rule realism and a concern with the role symbols play in human cognitive functioning, which was prevalent as a consequence of artificial intelligence research. The surge in philosophical interest waned, possibly in part due to the efforts of some traditionalists and the so-called black box problem. Most recently, what may be thought of as a third phase of connectionist research, based on so-called deep learning methods, is beginning to show some signs of again exciting philosophical interest. (shrink)