An adaptive function neural network(ADFUNN) for phrase recognition

Abstract

We describe an adaptive function neural network (ADFUNN) by the authors (2005), and apply it to the natural language processing task of phrase recognition. ADFUNN is based on a linear piecewise neuron activation function that is modified by a novel gradient descent supervised learning algorithm. Linearly inseparable problems can he learned with ADFUNN, rapidly and without hidden neurons. We perform phrase recognition on a set of phrases from the Lancaster parsed corpus (LPC) by R. Garside, et al. (1987). Generalisation rises to 100% with 150 training patterns (out of a total of 254).