Application of Connectionist Models to Animal Learning: Interactions between Perceptual Organization and Associative Processes

Application of Connectionist Models to Animal Learning: Interactions between Perceptual Organization and Associative Processes

Robert C. Honey (Cardiff University, UK) and Christopher S. Grand (Cardiff University, UK)
DOI: 10.4018/978-1-60960-021-1.ch001

Abstract

Here the authors examine the nature of the mnemonic structures that underlie the ability of animals to learn configural discriminations that are allied to the XOR problem. It has long been recognized that simple associative networks (e.g., perceptrons) fail to provide a coherent analysis for how animals learn this type of discrimination. Indeed “The inability of single layer perceptrons to solve XOR has a significance of mythical proportions in the history of connectionism.” (McLeod, Plunkett & Rolls, 1998; p. 106). In this historic context, the authors describe the results of recent experiments with animals that are inconsistent with the theoretical solution to XOR provided by some multi-layer connectionist models. The authors suggest a modification to these models that parallels the formal structure of XOR while maintaining two principles of perceptual organization and learning: contiguity and common fate.
Chapter Preview
Top

Contiguity, Similarity And Common Fate

There is good evidence that temporal proximity and similarity are influential parameters in studies of simple Pavlovian conditioning: The development of conditioned responding during pairings of one stimulus with another is often more rapid when both stimuli are presented in close temporal contiguity (e.g., Schneiderman & Gormezano, 1964; Mahoney & Ayres, 1976) and when the two stimuli are similar to one another (e.g., Grand, Close, Hale & Honey, 2007; Rescorla & Furrow, 1977; Rescorla & Gillan, 1980). That is, the Gestalt psychologists' observations concerning perceptual organization find obvious empirical analogues in studies of a form of learning that has been interpreted in associative terms since its original description (see Pavlov, 1927).

Complete Chapter List

Search this Book:
Reset