Talvez você curta
Video lectures, Stanford CS109 Introduction to Probability for Computer Scientists 2022, by Chris Piech web.stanford.edu/class/archive/… youtube.com/playlist?list=…
🎉Two free masterpiece book PDFs for mathematical ML/AI: -1/ "Mathematics for machine learning" (CUP, 2020). mml-book.github.io -2/ "Information theory, inference and learning algorithms" by Sir MacKay combining Information Theory with ML inference.org.uk/itila/book.html
I'm happy to announce the start of a new free and open online course on neuroscience for people with a machine learning or similar background, co-developed by @MarcusGhosh. YouTube Videos and Jupyter-based exercises will be released weekly. There is a Discord for discussions.
I'm making a list of NLP faculty who are recruiting PhD students: forms.gle/k8xkEzVGWD95fk… Results are shared here (after I confirm the submission): docs.google.com/spreadsheets/d… This is an experiment intended to help students find advisers and help advisers find students
BitTorrent is a fascinating piece of code and the algorithms that power this distributed system are mind-blowingly awesome 🤯 I have a full-blown BitTorrent Internals series on YouTube (7 videos) that covers literally everything you need to know to re-implement it in your…
Sometimes the best expositive content is buried in papers that provide it as context their readers. I came across this great description of modern GPU computing in an algorithms paper exploring applying GPUs to constraint problems. web.ecs.syr.edu/~ffiorett/file…
Anyone who would like to delve in #GenerativeAI and would like to get some hands-on (I provide some code too). Knowing some math and Python should suffice. Book: link.springer.com/book/10.1007/9… Code: github.com/jmtomczak/intr…
Why tune optimizers hyperparameters (ex. Adam) by hand, if one can train a neural network to behave like an optimizer and dynamically find the best update for your neural network’s weights? In this video, we explain the VeLO learned optimizer!👇 📺 youtu.be/9a6PQJxzUpM
Tired of tuning your neural network optimizer? Wish there was an optimizer that just worked? We’re excited to release VeLO 🚲, the first hyperparameter-free learned optimizer that outperforms hand-designed optimizers on real-world problems: velo-code.github.io 🧵
Twitter Architecture 2022 vs. 2012. What’s changed over the past 10 years? Thank you, @elonmusk for the transparency. {1/2}
- Find fields of interest, do literature review - Replicate interesting papers, showcase on GitHub - Think of ideas to follow up the papers - Reach out to paper authors, discuss your ideas - Implement your ideas, showcase on GitHub - Iterate to success
Incomplete path to research engineering: - Study calculus, lin. algebra, prob. theory - Intro courses e.g. fast.ai, deeplearning.ai - Advanced courses e.g. cs231n.stanford.edu, cs224n.stanford.edu - Join communities e.g. eleuther.ai
If you know,you know
United States Tendências
- 1. #WWERaw 35,6 B posts
- 2. Gunther 10,6 B posts
- 3. NASCAR 13,9 B posts
- 4. The Chase 47,4 B posts
- 5. Bryson 3.005 posts
- 6. Texans 31,6 B posts
- 7. Rick Bowness N/A
- 8. Brooks 12,7 B posts
- 9. PGA Tour 5.185 posts
- 10. Wirtz 14,4 B posts
- 11. Mark Ruffalo 173 B posts
- 12. Xabi 373 B posts
- 13. Dean Evason N/A
- 14. Lego 50,8 B posts
- 15. Barnsley 21,7 B posts
- 16. Powell 449 B posts
- 17. John Pork 2.041 posts
- 18. SAVE Act 130 B posts
- 19. Adam Pearce 1.403 posts
- 20. Claude Cowork 1.984 posts
Something went wrong.
Something went wrong.