Abstract | ||
---|---|---|
We introduce and discuss the application of statistical physics concepts in the context of on-line machine learning processes. The consideration of typical properties of very large systems allows to perfom averages over the randomness contained in the sequence of training data. It yields an exact mathematical description of the training dynamics in model scenarios. We present the basic concepts and results of the approach in terms of several examples, including the learning of linear separable rules, the training of multilayer neural networks, and Learning Vector Quantization. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-01805-3_1 | Similarity-Based Clustering |
Keywords | DocType | Volume |
statistical mechanics,linear separable rule,training data,basic concept,on-line machine,multilayer neural network,exact mathematical description,on-line learning,training dynamic,learning vector quantization,large system,model scenario,statistical physics,machine learning | Conference | 5400 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.38 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Biehl | 1 | 784 | 62.50 |
Nestor Caticha | 2 | 16 | 3.81 |
Peter Riegler | 3 | 1 | 1.06 |