A learning algorithm of multilaver dynamics associative neural network based on generalized hebb rule

Albrrad-Multilay erdynsm*sarsocia tivenwraln~ork~~ is a spa.cjoint random architeeturr with feedback The neees~~ly for the existem of the architffhup show that the research for synaptic weight haining ip in need. In the Gmt, the pap analyzes the differenoe between Inultilayer dynamics dtive network with double layer associative nymo'y network, BS well as the resemblance with discrete Hopfield nehvork by physics model Then, it proves the stability of !earning Plgorithm of multilayer dynamics associatiVe nehvork based on genernlhed Hebb rule in mathematics The 6mulahi.e experiment for the algorithm getr 6ne result and SOW a fundamental Bue of muhilayer .dynamiw dhe nerve in enginewing praciicea and researeh in "ly. IkTm-MukiLpw-eGenemlired Hebb rule, Discmte Hopfipldnehwrk, SynrIpbc wpigks Lyqunov fdn I. QUES~ONTO~~~~OUI