|
For Full-Text PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
|
A Modified Information Criterion for Automatic Model and Parameter Selection in Neural Network Learning
Sumio WATANABE
Publication
IEICE TRANSACTIONS on Information and Systems
Vol.E78-D
No.4
pp.490-499 Publication Date: 1995/04/25 Online ISSN:
DOI: Print ISSN: 0916-8532 Type of Manuscript: PAPER Category: Bio-Cybernetics and Neurocomputing Keyword: information criterion, AIC, MDL, weight pruning, prediction error, generalized learning,
Full Text: PDF>>
Summary:
This paper proposes a practical training algorithm for artificial neural networks, by which both the optimally pruned model and the optimally trained parameter for the minimum prediction error can be found simultaneously. In the proposed algorithm, the conventional information criterion is modified into a differentiable function of weight parameters, and then it is minimized while being controlled back to the conventional form. Since this method has several theoretical problems, its effectiveness is examined by computer simulations and by an application to practical ultrasonic image reconstruction.
|
|
|