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: In 2023 which is the best path to get good at machine and deep learning?

38 pointsby newsoulover 1 year ago
Which is the best resource (book, public course, blogs, etc) to get started in machine and deep learning and then get good at it both as a practitioner and from theoretical understanding?<p>The ultimate goal is to become a good at implementing models and come up with new ones.<p>Is there something like teachyourselfCS but for Data Science, ML and DL?

7 comments

GoldenMonkeyover 1 year ago
Caltech machine learning intro course: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=mbyG85GZ0PI">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=mbyG85GZ0PI</a><p>karpathy&#x27;s Zero to Hero series (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ">https:&#x2F;&#x2F;www.youtube.com&#x2F;playlist?list=PLAqhIrjkxbuWI23v9cThs...</a>)<p>meta llama 2 - is open source <a href="https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;llama&#x2F;tree&#x2F;main">https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;llama&#x2F;tree&#x2F;main</a><p>Tools:<p>ai - hosting Banana - Machine Learning Model Deployment on Serverless GPUs <a href="https:&#x2F;&#x2F;www.banana.dev" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.banana.dev</a><p>pinecone - vector database: <a href="https:&#x2F;&#x2F;www.pinecone.io" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.pinecone.io</a><p>how to run AI language models on a single cpu pc - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34869960">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=34869960</a>
评论 #37267004 未加载
max_over 1 year ago
For the basics read Micheal&#x27;s Neural Nets &amp; Deep learning - <a href="http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;" rel="nofollow noreferrer">http:&#x2F;&#x2F;neuralnetworksanddeeplearning.com&#x2F;</a><p>The Watch the Caltech telecourse - <a href="https:&#x2F;&#x2F;work.caltech.edu&#x2F;telecourse" rel="nofollow noreferrer">https:&#x2F;&#x2F;work.caltech.edu&#x2F;telecourse</a><p>Read tutorials on Pytorch, Tensorflow &amp; Keras.<p>Read, source codes on hugging face and deploys, test, train toy models.<p>Test your skills by participating in Data scientist competitions like Kaggle or Numerai.<p>It will give you a great way of guaging your competence with other data scientists.
brudgersover 1 year ago
Starting is binary not continuous.<p>Starting is the best way to get started.<p>Stasis cannot be motion optimized. Motivation is the hardest part. Everything else is about equally difficult because all the rest is experience. Good luckz.
评论 #37266342 未加载
tikkunover 1 year ago
I collected some resources on this. See: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=36195527">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=36195527</a>
pizzaover 1 year ago
the light way: fast.ai<p>the heavy way: kevin murphy&#x27;s a probabilistic approach to machine learning. you could make use of this book basically every day.
ggr2342over 1 year ago
Start with fast.ai courses for learning Deep Learning at the practitioner level.
YossarianFrPrezover 1 year ago
Once you&#x27;ve learned what you can from online resources and textbooks, doing projects -- from Kaggle, etc. -- is a good way to practice applying what you&#x27;ve learned.