Title :
Modeling neural network semantics
Author :
Healy, Michael J.
Author_Institution :
Boeing Co., Seattle, WA, USA
Abstract :
Summary form only given, as follows. Simplifying assumptions allow identification of the logical equivalent of the computations in a class of neural networks. Higher-order functions encapsulate the semantic content of patterns of signals and synaptic weights by forming formulas in a formal logic. This model was applied to capture the semantic content of a simple, hierarchical network that learns to identify the cardinalities of subsets of a finite set
Keywords :
formal logic; grammars; neural nets; formal logic; hierarchical network; neural network semantics; signal patterns; subset cardinality identification; synaptic weights; Computer networks; Logic; Neural networks; Postal services;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155619