6533b7d5fe1ef96bd12649b1

RESEARCH PRODUCT

Statistical analysis of multilayer perceptrons performances

Remus BradI.z. MihuMacarie Breazu

subject

Nonlinear systemSeries (mathematics)Computer sciencebusiness.industryInitializationStatistical analysisArtificial intelligencePerceptronbusinessAlgorithm

description

The paper is based on a series of studies on the learning capabilities of multilayered perceptrons (MLP). The complexity of these nonlinear systems can be varied, acting for instance on the number of hidden units, but we will be confronted with a choice dilemma, concerning the optimal complexity of the system for a given problem. By the mean of statistical methods, we have found that the effective number of hidden units is smaller than the potential size; some units have a "binary" activation level or a time constant activation. We also prove that weight initialization to small values is recommended and reduce the effective size of the hidden layer.

yearjournalcountryeditionlanguage
2002-11-13IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)
https://doi.org/10.1109/ijcnn.2001.938816