gradient descent method

基本解釋

Two ways are used to design the network, the one is the direct energy descent method, and the other is the gradient descent method.
有兩種方法可以用來設計網(wǎng)絡，一是能量下降法，另一個是梯度下降法。
The essence of back propagation networks is that make the change of weights become little by gradient descent method and finally attain the minimal error.
其實質(zhì)是采用梯度下降法使權值的改變總是朝著誤差變小的方向改進，最終達到最小誤差。
Instead of gradient descent method, recursive least-square algorithm is used to train the fuzzy neural network to overcome the defect of the low convergence rate and local minimal.
為了克服傳統(tǒng)的梯度下降法收斂速度慢、容易陷入局部極小值的缺點，該方案采用遞推最小二乘法訓練模糊神經(jīng)網(wǎng)絡。