Exact Calculation of the Hessian Matrix for the Multilayer Perceptron
- 1 July 1992
- journal article
- Published by MIT Press in Neural Computation
- Vol. 4 (4), 494-501
- https://doi.org/10.1162/neco.1992.4.4.494
Abstract
The elements of the Hessian matrix consist of the second derivatives of the error measure with respect to the weights and thresholds in the network. They are needed in Bayesian estimation of network regularization parameters, for estimation of error bars on the network outputs, for network pruning algorithms, and for fast retraining of the network following a small change in the training data. In this paper we present an extended backpropagation algorithm that allows all elements of the Hessian matrix to be evaluated exactly for a feedforward network of arbitrary topology. Software implementation of the algorithm is straightforward.Keywords
This publication has 1 reference indexed in Scilit:
- A FAST PROCEDURE FOR RETRAINING THE MULTILAYER PERCEPTRONInternational Journal of Neural Systems, 1991