A new gradient descent algorithm for unconstrained optimization problem is proposed. 提出了一种新的无约束优化下降算法。
BP neural network, as its nature of gradient descent method, is easy to fall into local optimum. 但BP神经网络本质是梯度下降(GD)法,容易陷入局部最优。
Therefore, this article puts forward to new dynamic neural networks with integrator and adjustable feedback coefficient and gets its learning algorithms by gradient descent. 为此,提出了一种由带有积分器和可调反馈系数的神经元构成的动力学神经网络,并利用梯度下降(GD)法得到了网络的学习算法。
Thorax multimodal medical image registration based on adaptive free-form deformation and gradient descent 基于自适应自由变形法和梯度下降(GD)法的胸部多模医学图像配准
Application of Improved Gradient Descent(GD) by BP Algorithm to Groundwater Level Forecast 改进梯度下降(GD)BP算法在地下水位预测中的应用