|
BP（Back Propagation）網(wǎng)絡(luò)是1986年由Rumelhart和McCelland為首的科學(xué)家小組提出，是一種按誤差逆?zhèn)鞑ニ惴ㄓ?xùn)練的多層前饋網(wǎng)絡(luò),，是目前應(yīng)用最廣泛的神經(jīng)網(wǎng)絡(luò)模型之一,。BP網(wǎng)絡(luò)能學(xué)習(xí)和存貯大量的輸入-輸出模式映射關(guān)系，而無需事前揭示描述這種映射關(guān)系的數(shù)學(xué)方程,。它的學(xué)習(xí)規(guī)則是使用最速下降法,，通過反向傳播來不斷調(diào)整網(wǎng)絡(luò)的權(quán)值和閾值，使網(wǎng)絡(luò)的誤差平方和最小,。BP神經(jīng)網(wǎng)絡(luò)模型拓?fù)浣Y(jié)構(gòu)包括輸入層（input）,、隱層(hide layer)和輸出層(output layer)。 Neural Network ToolboxDesign and simulate neural networks
Neural Network Toolbox™ provides tools for designing, implementing, visualizing, and simulating neural networks. Neural networks are used for applications where formal analysis would be difficult or impossible, such as pattern recognition and nonlinear system identification and control. Neural Network Toolbox supports feedforward networks, radial basis networks, dynamic networks, self-organizing maps, and other proven network paradigms.
|
|
|
FREE Product 
