Adaptive parameter pruning in neural networks

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 signi cance tests comparing autoprune to the new method lprune as well as to backpropagation with early stopping are given for 14 di erent problems. prechelt@icsi.berkeley.edu; permanent address: prechelt@ira.uka.de