SUPERVISED LEARNING ON LARGE REDUNDANT TRAINING SETS

• MARTIN MØLLER

  Computer Science Department, Århus University, Ny Munkegade, Building 540, DK-8000 Århus C, Denmark

Abstract

Efficient supervised learning on large redundant training sets requires algorithms where the amount of computation involved in preparing each weight update is independent of the training set size. Off-line algorithms like the standard conjugate gradient algorithms do not have this property while on-line algorithms like the stochastic backpropagation algorithm do. A new algorithm combining the good properties of off-line and on-line algorithms is introduced.

Journal

• International Journal of Neural Systems

  International Journal of Neural Systems 04 (01), 15-25, 1993-03

  World Scientific Pub Co Pte Lt

Keywords

• Computer Networks and Communications
• General Medicine

Details

• CRID: 1360574096185442560
• NII Article ID: 30009025231
• DOI: 10.1142/s0129065793000031
• ISSN: 17936462
• ISSN: 01290657
• Web Site: https://www.worldscientific.com/doi/pdf/10.1142/S0129065793000031
• Data Source:
  • Crossref
  • CiNii Articles