In this paper, we present the full deduction of the method to evaluate the Hessian matrix of a complex-valued feed forward neural network. The Hessian matrix is composed of the second derivatives of the error function of the network, and has many applications in network training and pruning algorithms, as well as in fast re-training of the network after a small change in training data. The software implementation of the presented method is straightforward.
CITATION STYLE
Popa, C. A. (2016). Exact hessian matrix calculation for complex-valued neural networks. In Advances in Intelligent Systems and Computing (Vol. 356, pp. 439–455). Springer Verlag. https://doi.org/10.1007/978-3-319-18296-4_36
Mendeley helps you to discover research relevant for your work.