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?
Caltech machine learning intro course:
<a href="https://www.youtube.com/watch?v=mbyG85GZ0PI">https://www.youtube.com/watch?v=mbyG85GZ0PI</a><p>karpathy's Zero to Hero series (<a href="https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ">https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThs...</a>)<p>meta llama 2 - is open source
<a href="https://github.com/facebookresearch/llama/tree/main">https://github.com/facebookresearch/llama/tree/main</a><p>Tools:<p>ai - hosting
Banana - Machine Learning Model Deployment on Serverless GPUs
<a href="https://www.banana.dev" rel="nofollow noreferrer">https://www.banana.dev</a><p>pinecone - vector database:
<a href="https://www.pinecone.io" rel="nofollow noreferrer">https://www.pinecone.io</a><p>how to run AI language models on a single cpu pc -
<a href="https://news.ycombinator.com/item?id=34869960">https://news.ycombinator.com/item?id=34869960</a>
For the basics read Micheal's Neural Nets & Deep learning
- <a href="http://neuralnetworksanddeeplearning.com/" rel="nofollow noreferrer">http://neuralnetworksanddeeplearning.com/</a><p>The Watch the Caltech telecourse
- <a href="https://work.caltech.edu/telecourse" rel="nofollow noreferrer">https://work.caltech.edu/telecourse</a><p>Read tutorials on Pytorch, Tensorflow & 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.
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.
I collected some resources on this. See: <a href="https://news.ycombinator.com/item?id=36195527">https://news.ycombinator.com/item?id=36195527</a>
the light way: fast.ai<p>the heavy way: kevin murphy's a probabilistic approach to machine learning. you could make use of this book basically every day.
Once you've learned what you can from online resources and textbooks, doing projects -- from Kaggle, etc. -- is a good way to practice applying what you've learned.