Bp. Vanmilligen et al., COMMENTS ON AN ACCELERATED LEARNING ALGORITHM FOR MULTILAYER PERCEPTRONS - OPTIMIZATION LAYER-BY-LAYER, IEEE transactions on neural networks, 9(2), 1998, pp. 339-341
This letter analyzes the performance of the neural network training me
thod known as optimization layer by layer.(1) We show, from theoretica
l considerations, that the amount of work required with OLL-Learning s
cales as the third power of the network size, compared with the square
of the network size for commonly used conjugate gradient training alg
orithms. This theoretical estimate is confirmed through a practical ex
ample. Thus, although OLL is shown to function very well for small neu
ral networks (less than about 500 weights per layer), it is slower tha
n CG for large neural networks. Second, we show that OLL does not alwa
ys improve on the accuracy that can be obtained with CG. It seems that
the final accuracy that can be obtained depends strongly on the initi
al network weights.