February
Papers
- Cramming: Training a Language Model on a Single GPU in One Day
- Open Problems in Applied Deep Learning
- Toolformer: Language Models Can Teach Themselves to Use Tools (Toolformer)
- MarioGPT: Open-Ended Text2Level Generation through Large Language Models
- Symbolic Discovery of Optimization Algorithms (Lion Optimizer)
- High-throughput Generative Inference of Large Language Models with a Single GPU (FlexGen)
- Multimodal Chain-of-Thought Reasoning in Language Models
- A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning
Links
- https://math.oxford.emory.edu/site/math117/besselCorrection/ Explaination of Bessel's Correction
- https://eli.thegreenplace.net/2016/the-softmax-function-and-its-derivative/ Computing the derivative of Softmax
- https://planetrl.github.io/ Learning Latent Dynamics for Planning from Pixels
- https://hardwarelottery.github.io/ The hardware lottery - Sara Hooker
- https://labs.kagi.com/ai/sum Universal text summariser
- https://www.underratedml.com/ Machine learning podcast about underrated ideas in ML
- https://atcold.github.io/pytorch-Deep-Learning/en/week07/07-1/ Energy-based machine learning models
- https://developers.google.com/machine-learning/glossary Machine learning glossary
- https://home.flywire.ai/ Whole-brain connectome of a Drosophila female brain
- https://alumni.media.mit.edu/~tpminka/statlearn/glossary/ Old list of machine learning topics
- https://atcold.github.io/NYU-DLSP21/en/week15/15-1/ Joint embedding models
- https://www.alignmentforum.org/s/yivyHaCAmMJ3CqSyj/p/LbrPTJ4fmABEdEnLf 200 open problems in mechanistic interpretability
- https://microscope.openai.com/models OpenAI's microscope tool for machanistic interpretability
- https://distill.pub/2020/circuits/zoom-in/ Zoom In: an introduction to circuits (mechanistic interpretability)
- https://www.nature.com/articles/d41586-022-03229-y Neurons in a dish learn to play pong (2022)
- https://vkrakovna.wordpress.com/2018/04/02/specification-gaming-examples-in-ai/ List of examples of specification gaming in AI
- https://compneuro.neuromatch.io/tutorials/intro.html The Neuromatch computational neuroscience course
- https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/ What is ChatGPT doing and why does it work? - Stephen Wolfwram
- https://ui.stampy.ai/ Comprehensive list of AI safety questions and answers
- https://www.deepspeed.ai/tutorials/ DeepSpeed tutorials of optimising training and inference for neural networks
- https://papers.nips.cc/ List of all papers presented at NeurIPS (1987 - 2021)
- https://grabbyaliens.com/ Grabby aliens
- https://lilianweng.github.io/ Good blog on variety of ML topics
- https://spinningup.openai.com/en/latest/index.html Educational resource on reinforcement learning by OpenAI