Mathematical Theory of Neural Networks
Final technical report 1 Jul 94-30 June 97.
RUTGERS - THE STATE UNIV NEW BRUNSWICKNJ
Pagination or Media Count:
This report focuses on fundamental theoretical issues relevant to the capabilities, performance, and limitations of artificial neural networks. For static feedforward networks, subjects of investigation included the study of error surfaces for least squares fitting, VC and other learning dimensions, representability questions. and function approximation. For dynamic recurrent nets, covered are questions dealing with parameter identification and modeling, realizability and other systems theoretic issues, theoretical computational capabilities, and learning-theoretic issues.
- Numerical Mathematics