This repo contains the instructions for the ML for Good bootcamp, for students and researchers interested in AI safety.
The curriculum draws inspiration from the redwood mlab, and ARENA, both of which focuses mainly on the ML engineering part. However there are a lot more workshops on strategy, goverance and conceptual AI safety during the ML4G.
- agents: agents, agents hard, agents normal
- evals: evals, evals hard, evals normal
- fsgm patch attack: fsgm patch attack
- gradcam: gradcam, gradcam hard, gradcam normal
- hyperparameters: hyperparameters
- image memory network: image memory network, image memory network normal
- induction heads: induction heads, induction heads hard, induction heads normal
- optimizers: optimizers, optimizers normal
- pytorch tuto: pytorch tuto
- rl: A2C workbook complete, A2C workbook empty hard, A2C workbook empty, DQN workbook complete, DQN workbook empty hard, DQN workbook empty
- rlhf: rlhf
- tensors: tensors
- transformer: transformer arena, transformer, transformer hard, transformer normal
- transformer interp: exercise hard, exercise normal, logit lens probing atlas old, solutions
- vanilla policy gradient: vanilla policy gradient
Before contributing to the project, you need to read the guidelines and follow the instructions in CONTRIBUTING.md.