Common Nature of Learning in BP and Hopfieldtype Neural Networks Solving an Underdetermined System of Linear Equations[J]. Acta Scientiarum Naturalium Universitatis SunYatseni, 2010,49(2):1-7.
Common Nature of Learning in BP and Hopfieldtype Neural Networks Solving an Underdetermined System of Linear Equations[J]. Acta Scientiarum Naturalium Universitatis SunYatseni, 2010,49(2):1-7.DOI:
The online solution of underdetermined linear equations is investigated by using two types of artificial neural networks (ie.
BP and Hopfieldtype neural networks). Although they differ from each other in terms of origins
network definition
structures and learning patterns
the BP and Hopfieldtype neural networks could be exploited for solving online such underdetermined linear equations and even possess a common mathematical formulation of learning and common computational abilities. In addition
based on zero initial values
the same but nonzero initial values and different random initial values
computersimulation and verification results are given. These substantiate well the efficacy and commonness of such two types of neural networks on solving underdetermined linear equations.
关键词
不定方程BP神经网络Hopfield神经网络学习同质性
Keywords
underdetermined equationBP neural networkHopfield neural networkcommon nature of learning