Parallel Distributed Processing, Volume 2: Explorations in the Microstructure of Cognition: Psychological and Biological ModelsWhat makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a new theory of cognition called connectionism that is challenging the idea of symbolic computation that has traditionally been at the center of debate in theoretical discussions about the mind. The authors' theory assumes the mind is composed of a great number of elementary units connected in a neural network. Mental processes are interactions between these units which excite and inhibit each other in parallel rather than sequential operations. In this context, knowledge can no longer be thought of as stored in localized structures; instead, it consists of the connections between pairs of units that are distributed throughout the network. Volume 1 lays the foundations of this exciting theory of parallel distributed processing, while Volume 2 applies it to a number of specific issues in cognitive science and neuroscience, with chapters describing models of aspects of perception, memory, language, and thought. |
Contents
VOLUME | 1 |
Schemata and PDP 20 Anatomy and 26 Reflections | 14 |
BASIC MECHANISMS 147 | 84 |
BIOLOGICAL MECHANISMS | 327 |
FORMAL ANALYSES | 363 |
An Analysis of the Delta Rule and the Learning | 444 |
Health through a Career Development AwardPHSMH00385to | 503 |
References | 507 |
Other editions - View all
Parallel Distributed Processing: Psychological and biological models David E. Rumelhart,James L. McClelland No preview available - 1986 |
Common terms and phrases
aspects axons behavior bottom-up broke capture categorical perception cells central word units cerebral cortex Chapter cognitive computational conceptual constraints context correct corresponding delta rule dendrites described detectors dimensions distributed model effects ending in t/d equation example excitatory experiment function goal hidden units hypotheses indicates inhibition input units interactive interpretation irregular verbs landmarks large number layer learning letter units lexical linear matrix mechanism memory Necker cube neocortex neural neurons nonlinear ocular dominance output unit parallel distributed processing parameters particular past tense pattern coordinates pattern of activation PDP models perception phoneme place fields present problem processing programmable modules prototype pyramidal cells regular representation represented response strength retrograde amnesia role rule Rumelhart schema schemata sentence shown in Figure shows simply simulation slot specific speech speech perception stimuli structure synapses thalamus tion TRACE Type unit coordinates vector view-field visual visual cortex weights Wickelfeatures Wickelphones