A Solution for the N-bit Parity Problem Using a Single Translated Multiplicative Neuron

被引：19
作者：
Eduardo Masato Iyoda
Hajime Nobuhara
Kaoru Hirota
机构：
[1] Tokyo Institute of Technology,Department of Computational Intelligence and Systems Science, Interdisciplinary Graduate School of Science and Engineering
来源：
Neural Processing Letters | 2003年 / 18卷 / 3期
关键词：
multiplicative neurons; -bit parity problem; neural networks;
D O I：
10.1023/B:NEPL.0000011147.74207.8c
中图分类号：
学科分类号：
摘要：
A solution to the N-bit parity problem employing a single multiplicative neuron model, called translated multiplicative neuron (πt-neuron), is proposed. The πt-neuron presents the following advantages: (a) ∀N≥1, only 1 πt-neuron is necessary, with a threshold activation function and parameters defined within a specific interval; (b) no learning procedures are required; and (c) the computational cost is the same as the one associated with a simple McCulloch-Pitts neuron. Therefore, the πt-neuron solution to the N-bit parity problem has the lowest computational cost among the neural solutions presented to date.
引用
收藏
页码：233 / 238
页数：5
相关论文
共 22 条
[1]  
Arslanov M. Z.(2002)-bit parity ordered neural networks Neurocomputing 48 1053-1056
[2]  
Ashigaliev D. U.(1993)-bit parity networks Neural Networks 6 607-608
[3]  
Ismail E. E.(1987)Learning, invariance, and generalization in high-order neural networks Applied Optics 26 4972-4978
[4]  
Brown D. A.(2002)Sigma-Pi cascade extended hybrid neural networks Journal of Advanced Computational Intelligence 6 126-134
[5]  
Giles C. L.(2000)On the exact solution of the Parity- Neural Networks 13 643-649
[6]  
Maxwell T.(2002) problem using ordered neural networks Neurocomputing 48 477-488
[7]  
Iyoda E. M.(1993)-bit parity neural networks: new solutions based on linear programming Neural Networks 6 705-707
[8]  
Hirota K.(2002)Parity with two layer feedforward nets Neural Computating 14 241-301
[9]  
Von Zuben F. J.(1997)On the complexity of computing and learning with multiplicative neurons Neurocomputing 16 225-235
[10]  
Lavretsky E.(1992)On the solution of the parity problem by a single hidden layer feedforward neural network Neural Networks 5 923-926
123