Simplification of a specific two-hidden-layer feedforward networks
Lei Chen, Guang-Bin Huang, C.K. Siew · 2004
A specific two-hidden-layer feedforward networks (TLFNs) proposed by G.B. Huang (2003) is presented in this paper. A method is introduced to simplify the structure of the TLFNs by introducing a new type of quantizers that unite two previous neurons A/sup (p)/ and B/sup (p)/ into a single neuron. Those new quantizers choose a special type of function as the neural network's activation function, which leads to the new TLFNs with 2/spl radic/((m+1)N) hidden neurons can learn N distinct samples (x/sub i/, t/sub i/) with negligibly small error, where m is the number of output neurons, and unlike Huang's TLFNs require 2/spl radic/((m+2)N) hidden neurons. Moreover, it is not necessary to estimate the quantizer value U defined in Huang's TLFNs, which is fixed in our new model of TLFNs. It can reduce significantly and markedly the complexity and computation of neural networks.