On the proper treatment of connectionism

Cognitive Science, 1982

Much of the progress in the fields constituting cognitive science has been based upon the use of explicit information processing models, almost exclusively patterned after conventional serial computers. An extension of these ideas to massively parallel, connectianist models appears to offer a number of advantages. After a preliminary discussion, this paper introduces a general connectionist model and considers how it might be used in cognitive science. Among the issues addressed are: stability and noise-sensitivity, distributed decisionmaking, time and sequence problems, and the representation of complex concepts.

Artificial Neural Networks -- Comparison of 3 Connectionist Models

Ai Magazine, 1988

Behavioral and Brain Sciences, 1990

Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and "simple" homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities (including "distributed representations") or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explore systematically the complex interaction between learning and representation, as we try to demonstrate through the analysis of several large networks.

Issues in Applied Linguistics, 2010

In previous issues of ML (cf. Fantuzzi, 1992, 1993), it was argued that connectionist explanations are too vague to qualify as theories of cognitive functions. Much of the argument hinges on the claim that hidden unit activation patterns of connectionist networks are currently too difficult to analyze, and that such opacity renders connectionist accounts virtually ineffective.

Although connectionism is advocated by its proponents as an alternative to the classical computational theory of mind, doubts persist about its computational credentials. Our aim is to dispel these doubts by explaining how connectionist networks compute. We first develop a generic account of computation—no easy task, because computation, like almost every other foundational concept in cognitive science, has resisted canonical definition. We opt for a characterisation that does justice to the explanatory role of computation in cognitive science. Next we examine what might be regarded as the ‘‘conventional’’ account of connectionist computation. We show why this account is inadequate and hence fosters the suspicion that connectionist networks are not genuinely computational. Lastly, we turn to the principal task of the paper: the development of a more robust portrait of connectionist computation. The basis of this portrait is an explanation of the representational capacities of connection weights, supported by an analysis of the weight configurations of a series of simulated neural networks.

2001

Connectionist approaches to cognitive modeling make use of large networks of simple computational units, which communicate by means of simple quantitative signals. Higher-level information processing emerges from the massivelyparallel interaction of these units by means of their connections, and a network may adapt its behavior by means of local changes in the strength of the connections.

2018

Computers have been used in every sphere of life and their role is increasing day by day, as newer and newer technologies are being developed. Artificial intelligence is at the heart of many exciting innovations. Representation forms the vital part of any AI application. If the representation is correct the half of the work is done. The connectionist approach is one of the ways to represent and identify any object in AI field. This approach has been successfully used and implemented in many of the real-life areas. The connectionist approach is based on the linking and state of any object at any time. An object has to mean with respect to its state and its links at a particular instant. It has many advantages for representation in AI field. Keyword: Artificial Intelligent, connectionist approach, symbolic learning, neural network.

Behavioral and Brain Sciences, 1990

Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities (including “distributed representations”) or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explo...

1988

Abstract: The difficulties that continually show up in connectionist modelling attempts directed towards high-level cognitive processing and knowledge representation include the inter-related problems of generative capacity, representational adequacy, variable binding, multiple instantiation of schemata (concepts, frames, etc.), rapid construction and modification of information structures, task control, and recursive processing.