Directions in Connectionist Research: Tractable Computations without Syntactically Structured Representations
نویسندگان
چکیده
(1981), the Cognitive Science Society meetings in 1984, and the publication of the PDP volumes (Rumelhart, McClelland, and the PDP Study Group, 1986, McClelland, Rumelhart, and the PDP Study Group, 1986). Figure 1: A prototypical example of a three-layer feed forward network, used by Plunkett and Marchman (1991) to simulate learning the past-tense of English verbs. The input units encode representations of the three phonemes of the present tense of the artificial words used in this simulation. The network is trained to produce a representation of the phonemes employed in the past tense form and the suffix (/d/, /ed/, or /t/) used on regular verbs. To run the network, each input unit is assigned an activation value of 0 or 1 , depending on whether the feature is present or not. Each input unit is connected to each of the 30 hidden units by a weighted connection and provides an input to each hidden unit equal to the product of the input unit's activation and the weight. Each hidden unit's activation is then determined by summing over the values coming from each input unit to determine a netinput, and then applying a non-linear function (e.g., the logistic function 1/(1+e). This whole procedure is Directions in Connectionist Research: Tractable Computations without Syntactically Structured Representations
منابع مشابه
Compositionality: A Connectionist Variation on a Classical Theme
Connectionism has been attacked on the grounds that it does not employ compo-sitionally structured representations (e.g., Fodor 8 Pylyshyn, 1988). This article develops the response that Connectionist models can, and in fact sometimes do, employ compositionally structured representations without, thereby. simply implementing a Classical " Language of Thought. " Focusing on the mode of combinati...
متن کاملHolistic Processing of Hierarchical Structures in Connectionist Networks
Despite the success of connectionist systems to model some aspects of cognition, critics argue that the lack of symbol processing makes them inadequate for modelling high-level cognitive tasks which require the representation and processing of hierarchical structures. In this thesis we investigate four mechanisms for encoding hierarchical structures in distributed representations that are suita...
متن کاملSyntactic Transformations on Distributed Representations
There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of ...
متن کاملClassical and Connectionist Models
My thesis is about the hypothesis that human cognitive processes employ a language of thought--a system of mental repesentation which supports syntactically complex mental symbols, physically realized in brains. First, I offer a formulation of this hypothesis which eliminates various obscurities in standard formulations. With this in hand, I suggest directions for empirical comparisons of class...
متن کاملConnectionism and the Problem of Systematicity
Systematicity is a pervasive property of cognitive behaviour (e.g., language and reasoning) whereby the ability to represent (systematicity of representation) and infer from (systematicity of inference) some instances of a structured object extends to other instances conforming to the same structure (Fodor & Pylyshyn, 1988; Fodor & McLaughlin, 1990). The problem of systematicity for a Connectio...
متن کامل