Conference proceeding
On the Probabilistic Interpretation of Neural Network Behavior
1987 American Control Conference, pp 1968-1972
Jun 1987
Abstract
Recent probabilistic interpretations of neural network models have suggested the formulaton of network operations in information-theoretic terms. In these interpretations, the neural network developes an assumed probability density function which represents its assumptions on the environment. Using a set of hypotheses, this probability density functon is shown to maintain an exponential relationship wth an energy-like functon that the network tends to minimize. The purpose of this note is to obtain this probability density function through Shannon's dervation of the entropy measure and Jaynes' maximum entropy principle. The main conclusion is that the neural network assumes the worst case (i.e. most uncertain or maximum-entropy) probability density function for the unknown environment.
Metrics
4 Record Views
Details
- Title
- On the Probabilistic Interpretation of Neural Network Behavior
- Creators
- Moshe Kam - Department of Electrical and Computer Engineering, Drexel University, Philadelphia, Pennsylvania 19104Allon Guez - Drexel University
- Publication Details
- 1987 American Control Conference, pp 1968-1972
- Conference
- 1987 American Control Conference
- Publisher
- IEEE
- Number of pages
- 1
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Other Identifier
- 991019182765704721