Title :
Neural processing of information
Author_Institution :
Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
Abstract :
A model is proposed in which the neuron serves as an information channel. An application of the Shannon information measures of entropy and mutual information taken together in the context of the proposed model lead to the Hopfield neuron model with a conditionalized Hebbian learning rule and sigmoidal transfer characteristic
Keywords :
Hebbian learning; Hopfield neural nets; maximum entropy methods; Hopfield neuron model; Shannon information measures; conditionalized Hebbian learning rule; information channel; information processing; maximum entropy; model; mutual information; neural processing; sigmoidal transfer characteristic; Analytical models; Biological information theory; Biological system modeling; Context modeling; Entropy; Equations; Laboratories; Mutual information; Neurons; Physics;
Conference_Titel :
Information Theory and Statistics, 1994. Proceedings., 1994 IEEE-IMS Workshop on
Conference_Location :
Alexandria, VA
Print_ISBN :
0-7803-2761-6
DOI :
10.1109/WITS.1994.513915
