This article puts forward a solution named divide - assemble by deducing the size of bp neural network to overcome entering the local best point , the dividing process is that a big bp neural network is divided into several small bp neural networks , every small bp neural network can study alone , after all small bp neural networks finish their study , we can assemble all these small bp neural networks into the quondam big bp neural networks ; on the basis of divide - assemble solution , this article discusses the preprocessing of input species and how to deduce the size of bp neural network further to make it easy to overcome entering the local best point ; for the study of every small bp neural network , this article adopts a solution named gdr - ga algorithm , which includes two algorithms . gdr ? a algorithm makes the merits of the two algorithms makeup each other to increase searching speed . finally , this article discusses the processing of atm band - width distribution dynamically 本文從bp網(wǎng)的結(jié)構(gòu)出發(fā),以減小bp神經(jīng)網(wǎng)絡(luò)的規(guī)模為手段來克服陷入局部極小點(diǎn),提出了bp神經(jīng)網(wǎng)絡(luò)的拆分組裝方法,即將一個(gè)大的bp網(wǎng)有機(jī)地拆分為幾個(gè)小的子bp網(wǎng),每個(gè)子網(wǎng)的權(quán)值單獨(dú)訓(xùn)練,訓(xùn)練好以后,再將每個(gè)子網(wǎng)的單元和權(quán)值有機(jī)地組裝成原先的bp網(wǎng),從理論和實(shí)驗(yàn)上證明了該方法在解決局部極小值這一問題時(shí)是有效的;在拆分組裝方法基礎(chǔ)上,本文詳細(xì)闡述了輸入樣本的預(yù)處理過程,更進(jìn)一步地減小了bp網(wǎng)絡(luò)的規(guī)模,使子網(wǎng)的學(xué)習(xí)更加容易了;對于子網(wǎng)的學(xué)習(xí),本文采用了最速梯度? ?遺傳混合算法(即gdr ? ? ga算法) ,使gdr算法和ga算法的優(yōu)點(diǎn)互為補(bǔ)充,提高了收斂速度;最后本文闡述了用以上方法進(jìn)行atm帶寬動(dòng)態(tài)分配的過程。