Author :
Chen, Fangyue ; Chen, Guanrong ; He, Guolong ; Xu, Xiubin ; He, Qinbin
Author_Institution :
Sch. of Sci., Hangzhou Dianzi Univ., Hangzhou, China
Abstract :
Universal perceptron (UP), a generalization of Rosenblatt´s perceptron, is considered in this paper, which is capable of implementing all Boolean functions (BFs). In the classification of BFs, there are: 1) linearly separable Boolean function (LSBF) class, 2) parity Boolean function (PBF) class, and 3) non-LSBF and non-PBF class. To implement these functions, UP takes different kinds of simple topological structures in which each contains at most one hidden layer along with the smallest possible number of hidden neurons. Inspired by the concept of DNA sequences in biological systems, a novel learning algorithm named DNA-like learning is developed, which is able to quickly train a network with any prescribed BF. The focus is on performing LSBF and PBF by a single-layer perceptron (SLP) with the new algorithm. Two criteria for LSBF and PBF are proposed, respectively, and a new measure for a BF, named nonlinearly separable degree (NLSD), is introduced. In the sense of this measure, the PBF is the most complex one. The new algorithm has many advantages including, in particular, fast running speed, good robustness, and no need of considering the convergence property. For example, the number of iterations and computations in implementing the basic 2-bit logic operations such as and, or, and xor by using the new algorithm is far smaller than the ones needed by using other existing algorithms such as error-correction (EC) and backpropagation (BP) algorithms. Moreover, the synaptic weights and threshold values derived from UP can be directly used in designing of the template of cellular neural networks (CNNs), which has been considered as a new spatial-temporal sensory computing paradigm.
Keywords :
Boolean functions; backpropagation; cellular neural nets; error correction; multilayer perceptrons; pattern classification; topology; 2-bit logic operation; CNN; DNA-like learning algorithm; LSBF class; MLP; NLSD; PBF class; Rosenblatt´s universal perceptron; SLP; UP; backpropagation algorithm; binary neural network training; biological system; cellular neural network design; convergence property; error-correction algorithm; linearly-separable Boolean function; multilayer perceptron; nonLSBF class; nonPBF class; nonlinearly separable degree; parity Boolean function; single-layer perceptron; spatial-temporal sensory computing paradigm; synaptic weight; threshold value; topological structure; Cellular neural network (CNN); DNA-like learning algorithm; linearly separable Boolean function (LSBF); multilayer perceptron (MLP); nonlinearly separable degree (NLSD); parity Boolean function (PBF); single-layer perceptron (SLP); universal perceptron (UP);