Abstract

The ability of neural networks to perform generalization by induction is the ability to learn an algorithm without the benefit of complete information about it. We consider the properties of networks and algorithms that determine the efficiency of generalization. These properties are described in quantitative terms. The most effective generalization is shown to be achieved by networks with the least admissible capacity. General conclusions are illustrated by computer simulations for a three-layered neural network. We draw a quantitative comparison between the general equations and specific results reported here and elsewhere.

Keywords

GeneralizationArtificial neural networkComputer scienceArtificial intelligenceNeural systemMathematicsAlgorithmMachine learningPsychologyMathematical analysisNeuroscience

MeSH Terms

AlgorithmsArtificial IntelligenceComputer SimulationModelsNeurological

Affiliated Institutions

Related Publications

Pruning algorithms-a survey

Russell Reed

A rule of thumb for obtaining good generalization in systems trained by examples is that one should use the smallest system that will fit the data. Unfortunately, it usually is ...

1993 IEEE Transactions on Neural Networks 1695 citations

Publication Info

Year
1989
Type
article
Volume
61
Issue
2
Pages
125-128
Citations
32
Access
Closed

External Links

Download PDF (Free) View on DOI.org PubMed Semantic Scholar

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

32
OpenAlex
0
Influential
29
CrossRef

Cite This

V. V. Anshelevich, Bagrat Amirikian, A. V. Lukashin et al. (1989). On the ability of neural networks to perform generalization by induction. Biological Cybernetics , 61 (2) , 125-128. https://doi.org/10.1007/bf00204596

Identifiers

DOI
10.1007/bf00204596
PMID
2742916

Data Quality

Data completeness: 81%