Title | ||
---|---|---|
Neural learning algorithms based on mappings: the case of the unitary group of matrices |
Abstract | ||
---|---|---|
Neural learning algorithms based on optimization on manifolds differ by the way the single learning steps are effected on the neural system's parameter space. In this paper, we present a class counting four neural learning algorithms based on the differential geometric concept of mappings from the tangent space of a manifold to the manifold itself. A learning stepsize adaptation theory is proposed as well under the hypothesis of additiveness of the learning criterion. The numerical performances of the discussed algorithms are illustrated on a learning task and are compared to a reference algorithm known from literature. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-74690-4_87 | ICANN (1) |
Keywords | Field | DocType |
numerical performance,unitary group,differential geometric concept,single learning step,reference algorithm,stepsize adaptation theory,neural system,tangent space,parameter space | Competitive learning,Semi-supervised learning,Stability (learning theory),Computer science,Empirical risk minimization,Wake-sleep algorithm,Algorithm,Unsupervised learning,Artificial intelligence,Computational learning theory,Machine learning,Learning classifier system | Conference |
Volume | ISSN | ISBN |
4668 | 0302-9743 | 3-540-74689-7 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Fiori | 1 | 494 | 52.86 |