书籍 Grokking Deep Learning的封面

Grokking Deep Learning

Andrew Trask

出版时间

2017-03-31

ISBN

9781617293702

评分

★★★★★
书籍介绍
Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks. Using only Python and its math-supporting library, NumPy, you'll train your own neural networks to see and understand images, translate text into different languages, and even write like Shakespeare! When you're done, you'll be fully prepared to move on to mastering deep learning frameworks.
用户评论
非常棒。最简单最基础最需要谨慎的思考,这事关建立优秀的直觉.看到后面突然惊觉,DL书包括本书都用到error这个词,而 这个词实际是严重误导了读者,我给取个更好的词, “How far left if I were to reach the target”, 简称“left“;input 和weight 本质上是对称的, forward propagation 与 back propagationyi'以及后面修改weight过程实际上非常符合人类的生活经验:微微旋动weight旋钮,input越大,到达target越快;微微旋动input 旋钮, weight 越大到底target 越快,当然不可能旋动中间层input,我们可以旋动该层前面的weigh。后面教做framework太用心了
This book helps to grasp some basic math concepts that under the hood of neural networks for those without classical math background. However, for me, some concepts and code are misconstructed and explained superficially. Comparing with this book, I recommend Make Your Own Neural Network written by Andrew Trask to deep learning beginners.
非常牛的一本书。
在调包类书籍泛滥的当下,这本书可以说是非常old school了,作者通过10多章的铺垫,最终完成了一个微型的深度学习库,这应该也是本书的最大价值。同时这本书的覆盖面和难度对初学者来说还是比较大的,读起来不像同系列的《算法图解》那样轻松。
示意图+基础代码简单入门
挺好的书,前十章是基础,从第十一章开始,难度陡然增加。我建议所有的初学者都应该把里面的代码都学会了,自己学习写个框架,然后自己操作,再去学习类似于pytorch,keras等框架。
Andrew Ng的Deep learning 替代本
适合入门
有的代码前后没改明白不能运行,MEAP版本最终版本都……