The learning algorithm is a process of chaos optimization, which can make the network avoid the local minima problem and false saturation phenomenon. 網(wǎng)絡(luò )的學(xué)習過(guò)程是一種混沌優(yōu)化算法，可有效避免普通神經(jīng)網(wǎng)絡(luò )的局部極值和假飽和現象的發(fā)生。
At the same time it can make the solution escape local extreme value and cause the overall optimization capacity when the solution approximates the minimum point. 當解逼近當前極小點(diǎn)的后，動(dòng)態(tài)方程又能使解逃逸局部極值，使其具有全局尋優(yōu)能力。
