Exact Calculation of the Hessian Matrix for the Multilayer Perceptron

DOI Web Site 4 Citations
  • Chris Bishop
    Neural Networks Group, AEA Technology, Harwell Laboratory, Oxfordshire, OX11 ORA, United Kingdom

Description

<jats:p> 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. </jats:p>

Journal

Citations (4)*help

See more

Details 詳細情報について

Report a problem

Back to top