gradient descent algorithm

基本解釋

A few or all of the parameters of the controller are adjusted by using the gradient descent algorithm to minimize the output error.
運(yùn)用最優(yōu)梯度下降法使目標(biāo)的計(jì)算值與期望值誤差最小來(lái)疊代優(yōu)選權(quán)重，建立疊代算法模型。
In the past thirty years, the work-horse algorithms in the field of digital signal processing and communication have been the gradient descent algorithm and the least square algorithm.
在過(guò)去的三十年中，數(shù)字信號(hào)処理和數(shù)字通信領(lǐng)域中採(cǎi)用的主要優(yōu)化算法是最速下降方法和最小二乘方法。
BP neural network also has strong nonlinear approximation ability, but its gradient descent algorithm determines that it easy falling into local optimum and sensitive to the initial values.
BP神經(jīng)網(wǎng)絡(luò)具有很強(qiáng)的非線性処理能力和逼近能力，但梯度下降的算法本質(zhì)決定了其具有容易陷入侷部最優(yōu)及初值敏感的缺點(diǎn)；
d.wanfangdata.com.cn