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.
评分非常棒。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
评分我同意,这本书前半部分特别用心,可以说是非常尽善尽美了,但是后半部分,特别是 LSTM 部分相当潦草。但是从整体上而言,这本书前面特别是到 CNN 的部分还是可取的,当然 LSTM 部分就看看吧。我给作者发邮件了,希望他能够在第二版改善吧。不过总体而言,在这个大家都喜欢用数学,用高深,不怎么对普通初学者友好对社区,这本书真是一股清流了。同时我觉得这本书的 MEAP 和 Published 版本可能区别很大,需要注意甄别。
评分No math,觉得非常友好通俗,有记忆点。作者还分享了学习心得,是通用的。虽然说起来容易做起来难。讲解问题的逐步深入。还讲了framework. 仰慕一下作者的学习能力和才思
评分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.
本站所有内容均为互联网搜索引擎提供的公开搜索信息,本站不存储任何数据与内容,任何内容与数据均与本站无关,如有需要请联系相关搜索引擎包括但不限于百度,google,bing,sogou 等
© 2025 onlinetoolsland.com All Rights Reserved. 本本书屋 版权所有