Accurate initialization of neural network weights by backpropagation of the desired response
Deniz Erdoğmuş, Óscar Fontenla-Romero, José Carlos Príncipe, Amparo Alonso‐Betanzos, Enrique Castillo, Robert Jenssen · 2004
Proper initialization of neural networks is critical for a successful training of its weights. Many methods have been proposed to achieve this, including heuristic least squares approaches. In this paper, inspired by these previous attempts to train (or initialize) neural networks, we formulate a mathematically sound algorithm based on backpropagating the desired output through the layers of a multilayer perceptron. The approach is accurate up to local first order approximations of the nonlinearities. It is shown to provide successful weight initialization for many data sets by Monte Carlo experiments.