LS-based training algorithm for neural networks

摘要

A new training algorithm is presented as a faster alternative to the backpropagation (BP) method. The new approach is based on the solution of a linear system at each step of the learning phase. The squared error at the output of each layer before the nonlinearity is minimized on the entire set of the learning patterns by a block least squares (LS) algorithm. The optimal weights for each layer are then computed by using the singular value decomposition (SVD) technique. The simulation results show considerable improvements from the point of view of both accuracy and speed of convergence.