Local search and pseudoinversion: an hybrid approach to neural network training
作者:Luca Rubini, Rossella Cancelliere, Patrick Gallinari, Andrea Grosso
摘要
We consider recent successful techniques proposed for neural network training that set randomly the weights from input to hidden layer, while weights from hidden to output layer are analytically determined by Moore–Penrose generalized inverse. This study aimed to analyse the impact on performances when the completely random sampling of the space of input weights is replaced by a local search procedure over a discretized set of weights. The performances of the proposed training methods are assessed through computational experience on several UCI datasets.
论文关键词:Neural networks, Random projections, Local search , Pseudoinverse matrix
论文评审过程:
论文官网地址:https://doi.org/10.1007/s10115-016-0935-y