Title | ||
---|---|---|
On-line learning with restricted training sets: exact solution as benchmark for general theories |
Abstract | ||
---|---|---|
We solve the dynamics of on-line Hebbian learning in perceptrons exactly, for the regime where the size of the training set scales linearly with the number of inputs. We consider both noiseless and noisy teachers. Our calculation cannot be extended to non-Hebbian rules, but the solution provides a nice benchmark to test more general and advanced theories for solving the dynamics of learning with restricted training sets. |
Year | Venue | Keywords |
---|---|---|
1998 | Proceedings of the 1998 conference on Advances in neural information processing systems II | exact solution,general theory,restricted training set |
Field | DocType | Volume |
Training set,Exact solutions in general relativity,Mathematical optimization,Computer science,Theoretical computer science,Hebbian theory,Artificial intelligence,Perceptron,Leabra,Machine learning | Conference | 11 |
ISSN | ISBN | Citations |
1049-5258 | 0-262-11245-0 | 0 |
PageRank | References | Authors |
0.34 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
H. C. Rae | 1 | 0 | 0.34 |
Peter Sollich | 2 | 298 | 38.11 |
A C Coolen | 3 | 19 | 10.70 |