TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Experts recommend Machine Learning books

150 点作者 dmonn将近 5 年前

6 条评论

henrik_w将近 5 年前
For a survey of AI and ML I really liked &quot;Artificial Intelligence – A Guide for Thinking Humans&quot; by Melanie Mitchell. I&#x27;ve written a summary of it here: <a href="https:&#x2F;&#x2F;henrikwarne.com&#x2F;2020&#x2F;05&#x2F;19&#x2F;artificial-intelligence-a-guide-for-thinking-humans&#x2F;" rel="nofollow">https:&#x2F;&#x2F;henrikwarne.com&#x2F;2020&#x2F;05&#x2F;19&#x2F;artificial-intelligence-a...</a>
cdavid将近 5 年前
The list is decent, but not exactly original.<p>For people w&#x2F; a physics background, I would still recommend <a href="https:&#x2F;&#x2F;www.inference.org.uk&#x2F;itprnn&#x2F;book.pdf" rel="nofollow">https:&#x2F;&#x2F;www.inference.org.uk&#x2F;itprnn&#x2F;book.pdf</a>. Some of it is a bit obsolete, but then DL made a lot of stuff around generalization&#x2F;overfitting somehow obsolete. It makes a lot of connection between different kind of approaches in ML, information theory, (Bayesian) statistics, and physics.<p>It is not a very good book if you only care about applications (in which case the Keras book, for beginner, or fastai&#x2F;etc. are much more appropriate).
评论 #24004410 未加载
melenaboija将近 5 年前
For NLP I would maybe add<p>Speech and Language Processing From Dan Jurafsky,<p>Available at: <a href="https:&#x2F;&#x2F;web.stanford.edu&#x2F;~jurafsky&#x2F;slp3&#x2F;" rel="nofollow">https:&#x2F;&#x2F;web.stanford.edu&#x2F;~jurafsky&#x2F;slp3&#x2F;</a>
inopinatus将近 5 年前
Slightly crestfallen that the “ML” here is machine learning and not the programming language. I still refer to my vintage paperback of L. C. Paulson’s <i>ML for the Working Programmer</i> from time to time.
评论 #23997986 未加载
newtohn99将近 5 年前
As a new grad (bachelors swe), is it worth it to jump on the ML hype train ? I see modelling is almost always only open to phds&#x2F;masters.<p>So is studying all that stuff just for being a MLE&#x2F; data engineer worth it, if you are already a software developer (full stack)?
评论 #24001298 未加载
评论 #24003372 未加载
horsemessiah将近 5 年前
State and Revolution is where I&#x27;d recommend people start for ML ;)
评论 #23999601 未加载
评论 #23997811 未加载