Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

@inproceedings{Rumelhart1986ParallelDP,
  title={Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations},
  author={David E. Rumelhart and James L. McClelland},
  year={1986}
}
The fundamental principles, basic mechanisms, and formal analyses involved in the development of parallel distributed processing (PDP) systems are presented in individual chapters contributed by leading experts. Topics examined include distributed representations, PDP models and general issues in cognitive science, feature discovery by competitive learning, the foundations of harmony theory, learning and relearning in Boltzmann machines, and learning internal representations by error… 

Figures from this paper

Parallel Distributed Processing at 25: Further Explorations in the Microstructure of Cognition
This paper introduces a special issue of Cognitive Science initiated on the 25th anniversary of the publication of Parallel Distributed Processing (PDP), a two-volume work that introduced the use of
Parallel Distributed Processing Theory in the Age of Deep Networks
  • J. Bowers
  • Computer Science
    Trends in Cognitive Sciences
  • 2017
Language Learning in Massively-Parallel Networks
TLDR
Massively-parallel connectionist networks have traditionally been applied to constraint-satisfaction in early visual processing, but are now being applied to problems ranging from the Traveling Salesman Problem to language acquisition.
Parallel distributed processing and neural networks: origins, methodology and cognitive functions.
TLDR
Parallel Distributed Processing (PDP), a computational methodology with origins in Associationism, is used to provide empirical information regarding neurobiological systems and considerable interest has shifted towards associative models.
Autonomous processing in parallel distributed processing networks
TLDR
This paper critically examines the claim that parallel distributed processing (PDP) networks are autonomous learning systems and argues that this is because these models are not adequately constrained by the properties of the functional architecture assumed by PDP modelers.
Parallel Distributed Processing: Implications for Cognition and Development
TLDR
The application of the connectionist framework to problems of cognitive development is considered, and a network that learns to anticipate which side of a balance beam will go down is illustrated, based on the number of weights on each side of the fulcrum and their distance from the Fulcrum.
Topological limits to the parallel processing capability of network architectures
TLDR
It is formally shown that, while the maximum number of tasks that can be performed simultaneously grows linearly with network size, under realistic scenarios (e.g. in an unpredictable environment), the expected number that could be performed concurrently grows radically sub-linearly withnetwork size.
Précis of Semantic Cognition: A Parallel Distributed Processing Approach
Abstract In this précis of our recent book, Semantic Cognition: A Parallel Distributed Processing Approach (Rogers & McClelland 2004), we present a parallel distributed processing theory of the
Parallel distributed processing models for economic systems and games
TLDR
The idea that neural networks and other parallel models of computation provide a natural way in which to model the working of an economic system and computational models implicit in descriptions of economic and social systems are developed.
Semantic Cognition: A Parallel Distributed Processing Approach
TLDR
The authors propose that performance in semantic tasks arises through the propagation of graded signals in a system of interconnected processing units, and show how a simple computational model proposed by Rumelhart exhibits a progressive differentiation of conceptual knowledge, paralleling aspects of cognitive development seen in the work of Frank Keil and Jean Mandler.
...
...