多年前我用来入门基础的书是 Kevin Gurney 写的《神经网络导论》（An Introduction to Neural Networks）。现在看有点过时了，但我依然觉得它很有价值。
The book I used to learn the basics many years ago was "An Introduction to Neural Networks", by Kevin Gurney. It's a bit outdated now, but I still consider it valuable.
…number of cost functions you can use for the last layer - softmax or cross-entropy are other possibilities that may be easier to understand, though possibly less performant for NLP tasks. I thought the introduction to neural networks from Andrew Ng's coursera course (even though it meant writing MATLAB) was quite good, and allows you to implement backprop, cost functions, etc. while still having some other helper code to make things…
…books don't interest me at all. If I wanted to learn some particular framework, I would just look up the documentation for that framework. I'm looking for two types of books: 1. A technical, math-heavy introduction to neural networks and deep learning, with little or no actual code (except possibly some pseudocode). The often recommended book by Goodfellow et al resembles what I'm looking for, but unfortunately, it completely lacks…
Hey, author here. Any/all feedback is welcome, and I'm happy to answer questions. Previous discussion on HN of the "introduction to Neural Networks" referenced in this article: https://news.ycombinator.com/item?id=19320217 Runnable code from the article: https://repl.it/@vzhou842/A-CNN-from-scratch-Part-1 Github: https://github.com/vzhou842/cnn-from-scratch
多年前我用来入门基础的书是 Kevin Gurney 写的《神经网络导论》（An Introduction to Neural Networks）。现在看有点过时了，但我依然觉得它很有价值。
The book I used to learn the basics many years ago was "An Introduction to Neural Networks", by Kevin Gurney. It's a bit outdated now, but I still consider it valuable.
……最后一层可以用的代价函数有许多种——softmax 或交叉熵是更容易理解的备选方案，不过在 NLP 任务上的性能可能差一些。我觉得吴恩达 Coursera 课程里的神经网络导论（尽管意味着要写 MATLAB）相当不错，它让你既能实现反向传播、代价函数等，同时又提供了一些辅助代码来搞定……
…number of cost functions you can use for the last layer - softmax or cross-entropy are other possibilities that may be easier to understand, though possibly less performant for NLP tasks. I thought the introduction to neural networks from Andrew Ng's coursera course (even though it meant writing MATLAB) was quite good, and allows you to implement backprop, cost functions, etc. while still having some other helper code to make things…
这是我见过最通俗易懂的神经网络入门教程。交互式的部分帮助很大，具体的例子也讲得很到位。
This is the most accessible introduction to Neural Networks I've found. The interactive bits really help as does the concrete example.
……这类书我一点兴趣都没有。如果我想学某个具体的框架，我直接去查那个框架的文档就行了。我在找两种书：1. 一本偏技术、偏数学的神经网络与深度学习入门书，几乎不包含或完全不包含实际代码（除了可能带点伪代码）。大家经常推荐的 Goodfellow 等人写的那本挺符合我的要求，但不幸的是，它完全缺少……
…books don't interest me at all. If I wanted to learn some particular framework, I would just look up the documentation for that framework. I'm looking for two types of books: 1. A technical, math-heavy introduction to neural networks and deep learning, with little or no actual code (except possibly some pseudocode). The often recommended book by Goodfellow et al resembles what I'm looking for, but unfortunately, it completely lacks…
嗨，我是作者。欢迎任何/所有反馈，我也很乐意回答问题。HN 之前对本文引用的“神经网络导论”的讨论：https://news.ycombinator.com/item?id=19320217 文章中可运行的代码：https://repl.it/@vzhou842/A-CNN-from-scratch-Part-1 Github：https://github.com/vzhou842/cnn-from-scratch
Hey, author here. Any/all feedback is welcome, and I'm happy to answer questions. Previous discussion on HN of the "introduction to Neural Networks" referenced in this article: https://news.ycombinator.com/item?id=19320217 Runnable code from the article: https://repl.it/@vzhou842/A-CNN-from-scratch-Part-1 Github: https://github.com/vzhou842/cnn-from-scratch