├── from-bits-to-intelligence └── README.md ├── README.md └── ilya_30u30 └── README.md /from-bits-to-intelligence/README.md: -------------------------------------------------------------------------------- 1 | 0. [From the transistor](https://github.com/geohot/fromthetransistor) 2 | 1. [The RISC-V Reader](http://www.riscvbook.com/) 3 | 2. [RISC-V Elf Spec](https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/master/riscv-elf.adoc) 4 | 3. [Crafting Interpreters](https://craftinginterpreters.com/) 5 | 4. [Tinygrad](https://github.com/tinygrad/tinygrad) 6 | 5. [Tinygrad notes](https://github.com/mesozoic-egg/tinygrad-notes/blob/main/README.md) 7 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # spike's ai resources # 2 | 3 | ilya_30u30: papers, lectures and other resources that were deemed most relevant by [ilya sutskever](https://en.wikipedia.org/wiki/Ilya_Sutskever) to understanding ml. 4 | 5 | from-bits-to-intelligence: books, specs and code to help understand the ml stack from first principles. 6 | 7 | [papers-anon's urls](https://rentry.org/LocalModelsLinks): papers, blogs, and other links related to local language models. 8 | 9 | [arpitingle gpu alpha](https://github.com/arpitingle/gpu-alpha): resources on gpu programming. 10 | -------------------------------------------------------------------------------- /ilya_30u30/README.md: -------------------------------------------------------------------------------- 1 | 1. [CS231n](https://cs231n.github.io/) 2 | 2. [Kolmogorov complexity](https://www.lirmm.fr/~ashen/kolmbook-eng-scan.pdf) 3 | 3. [Machine super intelligence](https://www.vetta.org/documents/Machine_Super_Intelligence.pdf) 4 | 4. [Minimum description length principle](https://arxiv.org/pdf/math/0406077.pdf) 5 | 5. [Scaling laws for Neuals LMs](https://arxiv.org/pdf/2001.08361.pdf) 6 | 6. [Deep speech 2](https://arxiv.org/pdf/1512.02595.pdf) 7 | 7. [Neural turing machines](https://arxiv.org/pdf/1410.5401.pdf) 8 | 8. [The coffee automaton](https://arxiv.org/pdf/1405.6903.pdf) 9 | 9. [Relational RNNs](https://arxiv.org/pdf/1806.01822.pdf) 10 | 10. [Variaional Lossy Autoencoder](https://arxiv.org/pdf/1611.02731.pdf) 11 | 11. [NN module for relational reasoning](https://arxiv.org/pdf/1706.01427.pdf) 12 | 12. [Identity mappings in DRNs](https://arxiv.org/pdf/1603.05027.pdf) 13 | 13. [Neural machine translation](https://arxiv.org/pdf/1409.0473.pdf) 14 | 14. [Attention is all you need](https://arxiv.org/pdf/1706.03762.pdf) 15 | 15. [Neural quantum chemistry](https://arxiv.org/pdf/1704.01212.pdf) 16 | 16. [Multi-scale context aggregation](https://arxiv.org/pdf/1511.07122.pdf) 17 | 17. [Deep resnets for image recognition](https://arxiv.org/pdf/1512.03385.pdf) 18 | 18. [GPipe: Scaling with microbatch pipeline](https://arxiv.org/pdf/1811.06965.pdf) 19 | 19. [Sequence to sequence for sets](https://arxiv.org/pdf/1511.06391.pdf) 20 | 20. [Image net classification with deep nets](https://proceedings.neurips.cc/paper_files/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf) 21 | 21. [Pointer networks](https://arxiv.org/pdf/1506.03134.pdf) 22 | 22. [Keeping neural nets simple](https://www.cs.toronto.edu/~hinton/absps/colt93.pdf) 23 | 23. [RNN regularization](https://arxiv.org/pdf/1409.2329.pdf) 24 | 24. [Understanding LSTMs](https://colah.github.io/posts/2015-08-Understanding-LSTMs/) 25 | 25. [Unreasonable effectiveness of RNNs](https://karpathy.github.io/2015/05/21/rnn-effectiveness/) 26 | 26. [First law of complexodynamics](https://scottaaronson.blog/?p=762) 27 | 27. [Annotated transformer](https://nlp.seas.harvard.edu/annotated-transformer/) 28 | --------------------------------------------------------------------------------