人工神经网络的互连权空间的演化方程学习算法

本文把人工神经网络的互连权视为广义的自旋变量，网络的学习问题看作互连权空间的优化问题，进而将通常在人工神经网络组态空间的连续时间动力学方程组推广到人工神经网络的互连权空间，并在方程组中引入类似Ｍｅｔｒｏｐｏｌｉｓ的ＭｏｎｔｅＣａｒｌｏ算法机制改进此方程组了以提高寻优能力，提出了一个人工神经网络的演化方程学习算法，该算法在很大程度上摆脱了局域极值的束缚，得到最优或接近最优的互连权，本文集中研究单层反

EVOLUTION EQUATION LEARNING ALGORITHM OF ARTIFICIAL NEURAL NETWORKS

n this paper the synaptic couplings of artificial neural networks are viewed as a general spin variable, considering the learning of the network as an optimal problem in synapticspace. As a result, the continuous-time dynamical coupled equations of pattern space ofneural network can be extended to synaptic space. An evolution equation learning algorithm is proposed with introducing a scheme similar to the Monte Carlo method proposedby Metropolis into these equations to improve the optimization ability. With this algorithm, the system can escape from the difficult of local extrema of the energy function andreach an optimal solution or its good approximations. This paper concentrate on singlelayered recurrent artificial neural networks. We use a quadric energy function in synapticcoupling space. We have studied the critical storage capacity ac of the networks whosesynaptic couplings are obtained with our algorithm. Computer simulation show that ac approximates to pseudo-inverse models when neuron number N is small and decreases slowlywith the increasing of N.