A Complexity Theory of Neural Networks
Annual technical rept. 15 Mar 1989-14 Mar 1990
PENNSYLVANIA STATE UNIV UNIVERSITY PARK DEPT OF COMPUTER SCIENCE AND ENGINEERING
Pagination or Media Count:
Significant results have been obtained on the computation complexity of analog neural networks, and distribute voting. The computing power and learning algorithms for limited precision analog neural networks have been investigated. Lower bounds for constant depth, polynomial size analog neural networks, and a limited version of discrete neural networks have been obtained. The work on distributed voting has important applications for distributed computation in the presence of faults, and the management of replicated databases. Keywords Neural networks, Complexity theory, Fault tolerance, Learning.
- Numerical Mathematics
- Computer Programming and Software
- Computer Systems