Pruning algorithms-a survey
Russell Reed · IEEE Transactions on Neural Networks · 1993
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.
Cited by 1,708 works. doi:10.1109/72.248452
Authors
References
- A Theory of the Learnable
- A theory of the learnable
- What Size Net Gives Valid Generalization?
- Learnability and the Vapnik-Chervonenkis dimension
- Consistent inference of probabilities in layered networks: predictions and generalizations
- Experiments on Learning by Back Propagation.
- Simplifying Neural Networks by Soft Weight-Sharing
- Comparing Biases for Minimal Network Construction with Back-Propagation
- Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
- A general lower bound on the number of examples needed for learning