优化器 | Little's Blogs #5
Description
https://chengaf.github.io/afcheng.github.io/2019/10/09/%E4%BC%98%E5%8C%96%E5%99%A8/
内容提要 Batch Gradient Descent (BGD)批梯度下降 Stochastic Gradient Descent (SGD) Mini-Batch Gradient Descent(MBGD) 改进措施: 动量Momentum的SGD; 牛顿加速梯度 Nesterov Accelerated Gradient; AdaDelta算法; Adam算法 Adaptive