The Complexity of Learning in Neural Networks - Theory and Application
Abstract
Randornized algorithms are proposed and analyzed for learning binary weights for a neuron and links to the theory of random graphs are established. Optimal stopping phenomena in gradient descent learning algorithms are characterized and explained in terms of a time-varying effective machine complexity. The finite sample performance of the k-nearest neighbor algorithm for pattern recognition is rigorously characterized. Tradeoffs in learning from mixtures of labeled and unlabeled examples are determined.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 02, 1996
- Accession Number
- ADA342305
Entities
People
- Santosh S. Venkatesh
Organizations
- Moore School of Electrical Engineering