A Complexity Theory of Neural Networks
Abstract
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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 14, 1990
- Accession Number
- ADA229432
Entities
People
- Georg Schnitger
- Ian Parberry
- Piotr Berman
Organizations
- Pennsylvania State University