zbMATH — the first resource for mathematics

Free energy-based competitive learning and minimum information production learning. (English) Zbl 1157.68423
Gammerman, A. (ed.), Artificial intelligence and applications. Machine learning. As part of the 26th IASTED international multi-conference on applied informatics. Calgary: International Association of Science and Technology for Development (IASTED); Anaheim, CA: Acta Press (ISBN 978-0-88986-710-9/CD-ROM). 395-400 (2008).
Summary: In this paper, we propose free energy-based competitive learning and its computational method called minimum information production learning. The free energy has been introduced to overcome the fundamental problem of information-theoretic competitive learning, that is, fidelity to input patterns. Mutual information maximization for competitive learning so far developed for competitive learning is unconstrained maximization. This means that final connection weights are not always faithful to input patterns. The free energy with built-in cost functions has been very useful in dealing with faithful representations. However, in the free energy, we have some cases where mutual information is degraded in the later stage of learning.
The new computational method of minimum information production learning has been introduced to stabilize learning in the later stage of learning. We applied the method to the famous Iris problem and a student survey. In both cases, we succeeded in increasing the performance in terms of training and generalization errors. In addition, we found that when information could not be increased, minimum information production learning made it possible to stabilize learning processes.
For the entire collection see [Zbl 1154.68012].
68T05 Learning and adaptive systems in artificial intelligence