Title :
Statistical method of pruning neural networks
Author_Institution :
Dept. of Math. & Stat., Maryland Univ., Baltimore, MD, USA
Abstract :
A statistical method of pruning multilayer perceptrons is proposed which is expected to involve less computation than does “optimal brain surgeon”. The statistical method iteratively performs the steps of estimating the error covariance of the weights, evaluating the z-statistics for the weights, pruning the weights selected by hypothesis testing, and re-training the neural network. An interesting relationship between the statistical method and “optimal brain surgeon” is discussed. The relationship provides some insight into these two methods
Keywords :
covariance matrices; iterative methods; learning (artificial intelligence); multilayer perceptrons; statistical analysis; covariance matrix; iterative method; learning; multilayer perceptrons; neural networks; pruning; statistical method; Artificial neural networks; Biological neural networks; Error analysis; Mathematics; Neural networks; Statistical analysis; Surges; Testing; Training data; Yttrium;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832626
