%0 Journal Article
%T LEARNING ALGORITHM FOR MEAN FIELD THEORY OF THE HIGHER-ORDER BOLTZMANN MACHINE<br>高阶Boltzmann机的平均场理论学习算法
%A Yuan Zheng Wang Baohan
%A <br>袁政
%A 王宝翰
%J 生物物理学报
%D 1993
%I 
%X Using mean field theory (MFT) of statistical mechanics and simulated annealing technique. the determinate equation of relaxation kinetics of higher-order Boltzmann Machine (BM) and its MFT learning algorithm are deduced in a way different from that in reference2], which is combined with the merits of general higher-order neural network and Boltzmann Machine. Both are easy to be implemented by VLSI. The learning algorithm saves a lot of CPU time. The computer simulation results for two-dimentional mirror symmetries and T-C problem show that the MFT learning algorithm of the third-order BM is correct and better than that of second-order BM.
%K Neural network Boltzmann machine Mean Field Theory learning algorithm<br>高阶
%K 玻尔兹曼机
%K 神经网络
%K 平均场
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=90BA3D13E7F3BC869AC96FB3DA594E3FE34FBF7B8BC0E591&jid=E0C9D9BBED813D6674AC13E942EAC86D&aid=58D679A24C28A03B7D8679EDB5013552&yid=D418FDC97F7C2EBA&vid=9CF7A0430CBB2DFD&iid=E158A972A605785F&sid=FED67FBA0A707330&eid=984BD2F4D19B9D1C&journal_id=1000-6737&journal_name=生物物理学报&referenced_num=0&reference_num=0