Pruning algorithms-a survey
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (5), 740-747
- https://doi.org/10.1109/72.248452
Abstract
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 not obvious what size is best; a system that is too small will not be able to learn the data while one that is just big enough may learn very slowly and be very sensitive to initial conditions and learning parameters. This paper is a survey of neural network pruning algorithms. The approach taken by the methods described here is to train a network that is larger than necessary and then remove the parts that are not needed.Keywords
This publication has 21 references indexed in Scilit:
- A comparison of weight elimination methods for reducing complexity in neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Generalization by weight-elimination applied to currency exchange rate predictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reduction of interconnection weights in higher order associative memory networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Frobenius approximation reduction method (FARM) for determining optimal number of hidden unitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A statistical approach to learning and generalization in layered neural networksProceedings of the IEEE, 1990
- A simple procedure for pruning back-propagation trained neural networksIEEE Transactions on Neural Networks, 1990
- Generalizing Smoothness Constraints from Discrete SamplesNeural Computation, 1990
- Consistent inference of probabilities in layered networks: predictions and generalizationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Improving generalization in backpropagation networks with distributed bottlenecksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A theory of the learnableCommunications of the ACM, 1984