In this paper , we profoundly research on the learning algorithm of neural networks after referring to lots of domestic and foreign scientific literature and give a practical classification algorithm under the non - linear separability condition 本論文在參考了大量國內(nèi)外有關(guān)科技文獻(xiàn)的基礎(chǔ)上,對神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法作了深入的研究,給出了切實(shí)可行的算法,主要解決了非線性樣本的分類問題。