The gamma MLP-using multiple temporal resolutions for improved classification

We (1996) have previously introduced the gamma multilayer perceptron (MLP) which is defined as an MLP with the usual synaptic weights replaced by gamma filters and associated gain terms throughout all layers. In this paper we apply the gamma MLP to a larger scale speech phoneme recognition problem, analyze the operation of the network, and investigate why the gamma MLP can perform better than alternatives. The gamma MLP is capable of employing multiple temporal resolutions. Furthermore, the gamma MLP is related to the "curse of dimensionality" and the ability of the gamma MLP to trade off temporal resolution for memory depth, and therefore increase memory depth without increasing the dimensionality of the network. The IIR MLP is a more general version of the gamma MLP. Investigation suggests that the error surface of the gamma MLP is more suitable for gradient descent training than the error surface of the IIR MLP.