深度学习算法与编程 (暂停更新)

深度学习算法与编程

前言

本书内容

• 内容提要
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/85162129

资料推荐

• 自学深度学习之计算机视觉的入门资料推荐
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/84076410

开源许可 LICENSE

所有的说明性文档基于 Creative Commons 协议, 所有的代码基于 MIT 协议.
All documents are licensed under the Creative Commons License, all codes are licensed under the MIT License.

软件版本

Python = 3.6
scikit-learn = 0.20.0
TensorFlow = 1.12
PyTorch = 1.0

损失函数

MSELoss

• 均方差损失函数MSELoss详解及反向传播中的梯度求导
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/85137756

cross-entropy

• 通过函数图像介绍信息熵的概念
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/85269091

• 案例详解cross-entropy交叉熵损失函数及反向传播
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/83962147

• Python和PyTorch对比实现cross-entropy交叉熵损失函数及反向传播
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/84029058

softmax

• softmax函数详解及误差反向传播的梯度求导
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/83959185

• 纯Python和PyTorch对比实现softmax及其反向传播
  – https://blog.youkuaiyun.com/oBrightLamp/article/details/84034658

softmax + cross-entropy

• 多标签softmax + cross-entropy交叉熵损失函数详解及反向传播中的梯度求导
  – https://blog.youkuaiyun.com/oBrightLa