INTERNATIONAL COMPUTER SCIENCE INSTITUTE
1947 Center St. ffl Suite 600 ffl Berkeley, California 94704-1198 ffl (510) 643-9153 ffl FAX (510) 643-7684
Adaptive Parameter Pruning in
Neural network pruning methods on the level of individual network parameters (e.g. connection weights) can improve generalization. An open problem in the pruning methods known today (OBD, OBS, autoprune, epsiprune) is the selection of the number of parameters to be removed in each pruning step (pruning strength). This paper presents a pruning method lprune that automatically adapts the pruning strength to the evolution of weights and loss of generalization during training. The method requires no algorithm parameter adjustment by the user. The results of extensive experimentation indicate that lprune is often superior to autoprune (which is superior to OBD) on diagnosis tasks unless severe pruning early in the training process is required. Results of statistical significance tests comparing autoprune to the new method lprune as well as to backpropagation with early stopping are given for 14 different problems.
?firstname.lastname@example.org; permanent address: email@example.com