TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: How do I get started with applied ML/AI/Deep Learning?

2 pointsby djangovmabout 8 years ago
Hi HN,<p>Small background: I have a degree in non-comp sci stream, but have been working as a dev&#x2F;lead startups&#x2F;corporates for last 10 years. Currently, I am in one of the big 4s as a SSE, but do not have any background in ML. Tech background would mostly be JVM...<p>So, how do I get started? Languages, technologies, books, projects, anything would help.

2 comments

Eridrusabout 8 years ago
There&#x27;s lots of books, courses, etc out there, much more than you can possible get around to reading. Lots of people recommend Andrew Ng&#x27;s ML course, and it&#x27;s a good introduction to the basic ideas, but it&#x27;s showing it&#x27;s age a bit IMO and doesn&#x27;t prepare you to be a practitioner at all.<p>Python is pretty much the lingua franca of machine learning, so expect to use that, and I would recommend Keras as a framework for getting started with deep learning; it uses TensorFlow (or Theano) under the hood. scikit-learn it the main non-DL python ML library. You will almost certainly want to use Jupyter as an interactive Python environment.<p>Things like WEKA&#x2F;deeplearning4j exist for the JVM, and they may be necessary for work, but are not where I would recommend starting.<p>If you&#x27;re not aware of Kaggle, it&#x27;s an ML competition website which hosts datasets, but also publishes descriptions of winning entries, though you&#x27;ll find that deep learning is not what wins everything.<p>I would also suggest looking at some of the academic papers from conferences like ICML&#x2F;NIPS&#x2F;ICLR or just uploaded to Arxiv (though figuring out which ones are interesting will be harder to start); many papers are surprisingly approachable and knowing what mathematical topics are mentioned in cutting edge papers can help guide your learning.
评论 #14289185 未加载
madrafiabout 8 years ago
Python Machine Learning is a great book to start the author made a great curriculum if you would like to follow it. <a href="https:&#x2F;&#x2F;sebastianraschka.com&#x2F;faq&#x2F;docs&#x2F;ml-curriculum.html" rel="nofollow">https:&#x2F;&#x2F;sebastianraschka.com&#x2F;faq&#x2F;docs&#x2F;ml-curriculum.html</a><p>This is mostly ML if you would like to dive into deep learning I think fast.ai is the best course for anyone with programming experience and you can also use the deeplearning.net Tutorial as a side reference. If you have a practical experience and would love to understand the theory behinds it then Deep Learning Book is the Bible.
评论 #14285786 未加载