Universal perceptron and DNA-like learning algorithm for binary neural networks: non-LSBF implementation

Authors:
Fangyue Chen;Guanrong Chen;Qinbin He;Guolong He;Xiubin Xu
Affiliations:
School of Science, Hangzhou Dianzi University, Zhejiang, China;Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China;Department of Mathematics, Taizhou University, Linhai, Zhejiang, China;Department of Mathematics, Zhejiang Normal University, Jinhua, Zhejiang, China;Department of Mathematics, Zhejiang Normal University, Jinhua, Zhejiang, China
Venue:
IEEE Transactions on Neural Networks
Year:
2009

Citing 9
Cited 3

The complexity of Boolean functions

The complexity of Boolean functions
The upstart algorithm: a method for constructing and training feedforward neural networks

Neural Computation
Fundamentals of Artificial Neural Networks

Fundamentals of Artificial Neural Networks
Artificial Intelligence: A Guide to Intelligent Systems

Artificial Intelligence: A Guide to Intelligent Systems
Cellular neural networks and visual computing: foundations and applications

Cellular neural networks and visual computing: foundations and applications
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)
Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations

IEEE Transactions on Neural Networks
The geometrical learning of binary neural networks

IEEE Transactions on Neural Networks
Classification of linearly nonseparable patterns by linear threshold elements

IEEE Transactions on Neural Networks

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations

IEEE Transactions on Neural Networks
Learning of dynamic BNN toward storing-and-stabilizing periodic patterns

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
A novel neural network parallel adder

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I

Quantified Score

Hi-index	0.01

Visualization

Abstract

Implementing linearly nonseparable Boolean functions (non-LSBF) has been an important and yet challenging task due to the extremely high complexity of this kind of functions and the exponentially increasing percentage of the number of non-LSBF in the entire set of Boolean functions as the number of input variables increases. In this paper, an algorithm named DNA-like learning and decomposing algorithm (DNA-like LDA) is proposed, which is capable of effectively implementing non-LSBF. The novel algorithm first trains the DNA-like offset sequence and decomposes non-LSBF into logic XOR operations of a sequence of LSBF, and then determines the weight-threshold values of the multilayer perceptron (MLP) that perform both the decompositions of LSBF and the function mapping the hidden neurons to the output neuron. The algorithm is validated by two typical examples about the problem of approximating the circular region and the well-known n-bit parity Boolean function (PBF).