cs231n-4---optimization

There are two ways to compute the gradient: A slow, approximate but easy way (numerical gradient), and a fast, exact but more error-prone way that requires calculus (analytic gradient). We will now present both.

analytic gradient：这里是指用subgradient近似后，不用再求导了。详见原文。

时间： 2024-10-08 21:48:57

cs231n-4---optimization的相关文章

CS231n 2017 学习笔记03——损失函数与参数优化 Loss Functions and Optimization

本博客内容来自 Stanford University CS231N 2017 Lecture 3 - Loss Functions and Optimization 课程官网:http://cs231n.stanford.edu/syllabus.html 从课程官网可以查询到更详细的信息,查看视频需要FQ上YouTube,如果不能FQ或觉得比较麻烦,也可以从我给出的百度云链接中下载. 课程视频&讲义下载:http://pan.baidu.com/s/1gfu51KJ 损失函数 Loss Fu

笔记：CS231n+assignment1（作业一）

CS231n的课后作业非常的好,这里记录一下自己对作业一些笔记. 一.第一个是KNN的代码,这里的trick是计算距离的三种方法,核心的话还是python和machine learning中非常实用的向量化操作,可以大大的提高计算速度. import numpy as np class KNearestNeighbor(object):#首先是定义一个处理KNN的类 """ a kNN classifier with L2 distance """

[CS231n-CNN] Training Neural Networks Part 1 : activation functions, weight initialization, gradient flow, batch normalization | babysitting the learning process, hyperparameter optimization

课程主页:http://cs231n.stanford.edu/ ? Introduction to neural networks -Training Neural Network ______________________________________________________________________________________________________________________________________________________________

cs231n-4---optimization