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。

Ask HN: What free resources did you use to learn how to program ML/AI?

415 点作者 acalderaro将近 8 年前

32 条评论

alexcnwy将近 8 年前
Firstly, while I think it&#x27;s beneficial to learn multiple languages (python, R, matlab, julia), I&#x27;d suggest picking one to avoid overwhelming yourself and freaking out. I&#x27;d suggest python because there are great tools and lots of learning resources out there, plus most of the cutting edge neural networks action is in python.<p>Then for overall curriculum, I&#x27;d suggest:<p>1. start with basic machine learning (not neural networks) and in particular, read through the scikit-learn docs and watch a few tutorials on youtube. spend some time getting familiar with jupyter notebooks and pandas and tackle some real-world problems (kaggle is great or google around for datasets that excite you). Make sure you can solve regression, classification and clustering problems and understand how to measure the accuracy of your solution (understand things like precision, recall, mse, overfitting, train&#x2F;test&#x2F;validation splits)<p>2. Once you&#x27;re comfortable with traditional machine learning, get stuck into neural networks by doing the fast.ai course. It&#x27;s seriously good and will give you confidence in building near cutting-edge solutions to problems<p>3. Pick a specific problem area and watch a stanford course on it (e.g. cs231n for computer vision or cs224n for NLP)<p>4. Start reading papers. I recommend Mendeley to keep notes and organize them. The stanford courses will mention papers. Read those papers and the papers they cite.<p>5. Start trying out your own ideas and implementations.<p>While you do the above, supplement with:<p>* Talking Machines and O&#x27;Reilly Data Show podcasts<p>* Follow people like Richard Socher, Andrej Karpathy and other top researchers on Twitter<p>Good luck and enjoy!
评论 #15000195 未加载
petrbela将近 8 年前
ML&#x2F;AI:<p>* <a href="https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;intro-to-artificial-intelligence--cs271" rel="nofollow">https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;intro-to-artificial-intellige...</a><p>* <a href="https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;machine-learning--ud262" rel="nofollow">https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;machine-learning--ud262</a><p>Deep Learning:<p>* Jeremy Howard&#x27;s incredibly practical DL course <a href="http:&#x2F;&#x2F;course.fast.ai&#x2F;" rel="nofollow">http:&#x2F;&#x2F;course.fast.ai&#x2F;</a><p>* Andrew Ng&#x27;s new deep learning specialization (5 courses in total) on Coursera <a href="https:&#x2F;&#x2F;www.deeplearning.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.deeplearning.ai&#x2F;</a><p>* Free online &quot;book&quot; <a href="http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;</a><p>* The first official deep learning book by Goodfellow, Bengio, Courville is also available online for free <a href="http:&#x2F;&#x2F;www.deeplearningbook.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.deeplearningbook.org&#x2F;</a>
larrydag将近 8 年前
Two good ebooks. Go well with R.<p>Introduction to Statistical Learning <a href="http:&#x2F;&#x2F;www-bcf.usc.edu&#x2F;~gareth&#x2F;ISL&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www-bcf.usc.edu&#x2F;~gareth&#x2F;ISL&#x2F;</a><p>Elements of Statistical Learning <a href="https:&#x2F;&#x2F;web.stanford.edu&#x2F;~hastie&#x2F;ElemStatLearn&#x2F;" rel="nofollow">https:&#x2F;&#x2F;web.stanford.edu&#x2F;~hastie&#x2F;ElemStatLearn&#x2F;</a>
lefnire将近 8 年前
* Course: fast.ai (<a href="http:&#x2F;&#x2F;course.fast.ai" rel="nofollow">http:&#x2F;&#x2F;course.fast.ai</a>). Practical, to the point, theory + code.<p>* Book: Hands-On Machine Learning w&#x2F; Scikit-Learn &amp; TensorFlow (<a href="http:&#x2F;&#x2F;amzn.to&#x2F;2vPG3Ur" rel="nofollow">http:&#x2F;&#x2F;amzn.to&#x2F;2vPG3Ur</a>). Theory &amp; code, starting from &quot;shallow&quot; learning (eg Linear Regression) on sckikit-learn, pandas, numpy; and moves to deep learning with TF.<p>* Podcast: Machine Learning Guide (<a href="http:&#x2F;&#x2F;ocdevel.com&#x2F;podcasts&#x2F;machine-learning" rel="nofollow">http:&#x2F;&#x2F;ocdevel.com&#x2F;podcasts&#x2F;machine-learning</a>). Commute&#x2F;exercise backdrop to solidify theory. Provides curriculum &amp; resources.
e_ameisen将近 8 年前
Online courses recommended in this thread are great resources to get your feet wet. If you want to actually be able to build ML powered applications, or contribute to an MLE team, we&#x27;ve written a blog post which is a distillation of conversations with over 50 top teams (big and small) in the Bay Area. Hope you find it helpful!<p><a href="https:&#x2F;&#x2F;blog.insightdatascience.com&#x2F;preparing-for-the-transition-to-applied-ai-d41e48403447" rel="nofollow">https:&#x2F;&#x2F;blog.insightdatascience.com&#x2F;preparing-for-the-transi...</a><p>Disclaimer: I work for Insight
superasn将近 8 年前
Andrew Ng&#x27;s tutorials[1] on Coursera are very good.<p>If you&#x27;re into python programming then tutorials by sentdex[2] are also pretty good and cover things like scikit, tensorflow, etc (more practical less theory)<p>[1] <a href="https:&#x2F;&#x2F;www.coursera.org&#x2F;learn&#x2F;machine-learning" rel="nofollow">https:&#x2F;&#x2F;www.coursera.org&#x2F;learn&#x2F;machine-learning</a> [2] <a href="https:&#x2F;&#x2F;pythonprogramming.net&#x2F;data-analysis-tutorials&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pythonprogramming.net&#x2F;data-analysis-tutorials&#x2F;</a>
mikekchar将近 8 年前
This doesn&#x27;t actually answer the question, but I always think that people who want to study neural nets should read Marvin Minsky&#x27;s Perceptrons. It&#x27;s an academic work. It&#x27;s short. It&#x27;s incredibly well written and easy to understand. It shaped the history of neural net research for decades (err... stopped it, unfortunately :-) ). You should be able to find it at any university library.<p>Although this recommendation doesn&#x27;t really fit the requirements of the poster, I think it is easy to reach first for modern, repackaged explanations and ignore the scientific literature. I think there is a great danger in that. Sometimes I think people are a bit scared to look at primary sources, so this is a great place to start if you are curious.
iamkeyur将近 8 年前
<a href="https:&#x2F;&#x2F;unsupervisedmethods.com&#x2F;over-150-of-the-best-machine-learning-nlp-and-python-tutorials-ive-found-ffce2939bd78" rel="nofollow">https:&#x2F;&#x2F;unsupervisedmethods.com&#x2F;over-150-of-the-best-machine...</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;ChristosChristofidis&#x2F;awesome-deep-learning" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ChristosChristofidis&#x2F;awesome-deep-learnin...</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;josephmisiti&#x2F;awesome-machine-learning" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;josephmisiti&#x2F;awesome-machine-learning</a>
orthoganol将近 8 年前
&quot;Learn AI the Hard Way&quot;. It&#x27;s actually just reading a bunch of papers and trying to implement them, and anytime you don&#x27;t understand something spend as much time as needed until you get it.
billconan将近 8 年前
<a href="http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;index.html" rel="nofollow">http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;index.html</a>
melonkernel将近 8 年前
1. Udacity: Machine Learning<p>2. Deep Learning Summer School Montreal 2016 <a href="https:&#x2F;&#x2F;sites.google.com&#x2F;site&#x2F;deeplearningsummerschool2016&#x2F;home" rel="nofollow">https:&#x2F;&#x2F;sites.google.com&#x2F;site&#x2F;deeplearningsummerschool2016&#x2F;h...</a><p>2. selfdrivingcars.mit.edu + youtube playlist &quot;MIT 6.S094: Deep Learning for Self-Driving Cars&quot; (<a href="https:&#x2F;&#x2F;youtu.be&#x2F;1L0TKZQcUtA?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;1L0TKZQcUtA?list=PLrAXtmErZgOeiKm4sgNOknGvN...</a>)<p>3. Coursera: Machine Learning with Andrew Ng<p>4. Standford Cs231n (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=g-PvXUjD6qg&amp;list=PLlJy-eBtNFt6EuMxFYRiNRS07MCWN5UIA" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=g-PvXUjD6qg&amp;list=PLlJy-eBtNF...</a>)<p>5. Deep Learning School 2016 (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLrAXtmErZgOfMuxkACrYnD2fTgbzk2THW" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLrAXtmErZgOfMuxkACrYn...</a>)<p>6. Udacity: Deep Learning (<a href="https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;deep-learning--ud730" rel="nofollow">https:&#x2F;&#x2F;www.udacity.com&#x2F;course&#x2F;deep-learning--ud730</a>)<p>I created a blog (<a href="http:&#x2F;&#x2F;ai.bskog.com" rel="nofollow">http:&#x2F;&#x2F;ai.bskog.com</a>) to have as a notepad and study backlog. There I keep track of what free courses I am currently taking and which one I will take next.<p>p.s.<p>Although video courses are good. Everyday life makes it sometimes difficult to listen to videos on youtube while for instance doing chores around the house or working out, because you often need to a. see the slides&#x2F;code examples, and b. put it into practice right away... therefore, podcasts are good to give you a flow of information.<p>Linear Digression, Data skeptic and (thanks to this thread i now discovered Machine Learning Guide)<p>Don&#x27;t be discouraged if there is stuff you do not understand or feel like: i can never remember these terms or that algorithm. Just be immersed in the information and stuff will fall into place. And later when you hear about that thing again it will make more sense. I tend to use a breadth first approach to learning, where i get exposed to everything before digging into details thus getting an overview of what i need to learn and where to start.
mindviews将近 8 年前
A study group meetup (Every Tuesday evening in Austin, TX): <a href="https:&#x2F;&#x2F;www.meetup.com&#x2F;cppmsg_ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.meetup.com&#x2F;cppmsg_ai&#x2F;</a><p>Just Q&amp;A - no presentations. Study from whatever books (<a href="http:&#x2F;&#x2F;amlbook.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;amlbook.com&#x2F;</a> and <a href="http:&#x2F;&#x2F;www.deeplearningbook.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.deeplearningbook.org&#x2F;</a> are popular in our group) or courses (Andrew Ng&#x27;s are also popular) you like throughout the week and then show up with any questions you have. We&#x27;ve been meeting for a couple of months now and new folks are always welcome no matter where you are in your studies!
jwatte将近 8 年前
I did the &quot;early years&quot; of both statistics and tiny neural networks&#x2F;perceptrons in college a long time ago. It also helps that I use math at work (anything from simulated 3D physics to DSP.)<p>Since then, I&#x27;ve used Wikipedia and Mathworld when work had needed it. Regression, random forest, simulated annealing, clustering, boosting and gradient ascent are all on the statistics&#x2F;ML spectrum.<p>But the best resource was running NVIDIA DIGITS, training some of the stock models, and really looking deeply at the visualizations available. You could do this on your own computer, or these days, rent some spot GPU instance on ECC for cheap.<p>I highly recommend going through the DIGITS tutorials if you want a crash course in deep learning, and make sure to visualize all the steps! Try a few different network topologies and different depths to get a feel for how it works.
deepnotderp将近 8 年前
For deep learning, and ConvNets in particular, cs231n can&#x27;t be beat.
modeless将近 8 年前
Geoff Hinton&#x27;s Coursera course was what got me into it. It&#x27;s not for the faint of heart. I might recommend Andrej Karpathy&#x27;s cs231n as a more up to date source today.
cs702将近 8 年前
Here&#x27;s a great curated list of resources:<p><a href="https:&#x2F;&#x2F;unsupervisedmethods.com&#x2F;my-curated-list-of-ai-and-machine-learning-resources-from-around-the-web-9a97823b8524" rel="nofollow">https:&#x2F;&#x2F;unsupervisedmethods.com&#x2F;my-curated-list-of-ai-and-ma...</a><p>HN thread: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14764700" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14764700</a>
jhealy将近 8 年前
This is only the tip of the iceberg, but I found this introduction to naive bayes classification assumed little prior knowledge and successfully helped me build a basic classifier: <a href="https:&#x2F;&#x2F;monkeylearn.com&#x2F;blog&#x2F;practical-explanation-naive-bayes-classifier&#x2F;" rel="nofollow">https:&#x2F;&#x2F;monkeylearn.com&#x2F;blog&#x2F;practical-explanation-naive-bay...</a>
sn9将近 8 年前
For the math: MIT OCW Scholar and maybe Klein&#x27;s <i>Coding the Matrix</i>.<p>For AI specifically, MOOCS on Coursera, edx, and Udacity will give you plenty of options. The ones by big names like Thrun, Norvig, and Ng are great places to start.<p>It really helps to already be comfortable with algorithms. Princeton&#x27;s MOOCs on Algorithms by Bob Sedgewick on Coursera would be a great place to start.
mongodude将近 8 年前
Think Bayes and Python Data Science Handbook are a good starting point. Below is the list of free books to learn ML&#x2F;AI<p><a href="http:&#x2F;&#x2F;blog.paralleldots.com&#x2F;data-scientist&#x2F;list-must-read-books-data-science&#x2F;" rel="nofollow">http:&#x2F;&#x2F;blog.paralleldots.com&#x2F;data-scientist&#x2F;list-must-read-b...</a>
garysieling将近 8 年前
<a href="https:&#x2F;&#x2F;www.findlectures.com&#x2F;?p=1&amp;class1=Technology&amp;category_l2_Technology=-Machine%20Learning" rel="nofollow">https:&#x2F;&#x2F;www.findlectures.com&#x2F;?p=1&amp;class1=Technology&amp;category...</a>
jongold将近 8 年前
Fast.ai is absolutely wonderful
baron816将近 8 年前
If you were to spend a year or so going through many of the resources presented here, and probably knew your stuff pretty well (or at least as well as you could after a year), would anyone actually give you a job?
评论 #15000676 未加载
评论 #15001968 未加载
Toast_将近 8 年前
The free Azure ML tutorials are pretty cool.<p><a href="https:&#x2F;&#x2F;gallery.cortanaintelligence.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;gallery.cortanaintelligence.com&#x2F;</a>
Dowwie将近 8 年前
There are too many resources from which to choose. It would be thoughtful of anyone to share AI learning pathways, like a syllabus, using those resources.
m15i将近 8 年前
www.fast.ai
yodaarjun将近 8 年前
For Deep Learning, deeplearning.ai has launched a free course on Coursera, which you may want to check out.
icc97将近 8 年前
So who else has signed up for the deeplearning.ai course then? (I just did)
sprobertson将近 8 年前
arxiv.org to learn the models, SemanticScholar to find connections between papers, GitHub search to find other people&#x27;s implementations
评论 #15001111 未加载
Frogolocalypse将近 8 年前
? I&#x27;ve always thought that ML&#x2F;AI for me was about learning the languages that could express my idea of how it could work. In order to do that myself, I started reading about algorithm types.<p><a href="http:&#x2F;&#x2F;machinelearningmastery.com&#x2F;a-tour-of-machine-learning-algorithms&#x2F;" rel="nofollow">http:&#x2F;&#x2F;machinelearningmastery.com&#x2F;a-tour-of-machine-learning...</a><p>There was one particular study piece that I remember reading that I believe was written in the late 70&#x27;s early 80&#x27;s, but I can&#x27;t remember its name. It was a HTML unformatted uni course-work document that the guy who wrote it said he&#x27;d just keep changing it as required. Really wish I could remember his name.<p>I have a slightly different bent on what is discussed here, because my particular implementation reflects what I think is important. There are an infinite number of variations. It depends on what you think you think it might be good for.
frik将近 8 年前
Are there good Deep Learning tutorials or blog posts with code (github) in Java, NodeJS, PHP, Lua, Swift or Go ?
评论 #15002000 未加载
jey将近 8 年前
persistence
palerdot将近 8 年前
If you are into watching programming videos, I would recommend Siraj Raval Youtube channel - <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;channel&#x2F;UCWN3xxRkmTPmbKwht9FuE5A" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;channel&#x2F;UCWN3xxRkmTPmbKwht9FuE5A</a><p>It is quirky, funny and above all very short and crisp and gives you a quick overview of things. Most of his videos are related to AI&#x2F;ML.
评论 #14999127 未加载
评论 #14998904 未加载
评论 #14998964 未加载
评论 #14998976 未加载
评论 #15001681 未加载