Name
Abstract | ||
|---|---|---|
A multilayer perceptron comprising a single hidden layer of neurons with sigmoidal transfer functions can approximate any computable function to arbitrary accuracy. The size of the hidden layer dictates the approximation capability of the multilayer perceptron and automatically determining a suitable network size for a given data set is an interesting question. This paper considers the problem of inferring the size of multilayer perceptron networks with the MMLD model selection criterion which is based on the minimum message length principle. The two main contributions of the paper are: (1) a new model selection criterion for inference of fully-connected multilayer perceptrons in regression problems, and (2) an efficient algorithm for computing MMLD-type codelengths in mathematically challenging model classes. Empirical performance of the new algorithm is demonstrated on artificially generated and real data sets. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/978-3-642-44958-1_20 | ALGORITHMIC PROBABILITY AND FRIENDS: BAYESIAN PREDICTION AND ARTIFICIAL INTELLIGENCE |
Field | DocType | Volume |
Minimum message length,Inference,Computer science,Algorithm,Model selection,Multilayer perceptron,Fisher information,Perceptron,Computable function,Sigmoid function | Conference | 7070 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.34 |
References | Authors | |
12 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Enes Makalic | 1 | 55 | 11.54 |
| Lloyd Allison | 2 | 1 | 0.34 |