66 | ML 7: De-noising Auto Encoders
- Published on
- ∘ ~33 mins ∘ ––– views
Machine-learning
- how do they work
63 | ML 6: Characterizations of Federated Learning
- Published on
- ∘ ~21 mins ∘ ––– views
Digest from a paper presented at NeurIPS '2438 | ML 5: If My Mother Had Wheels She Would Have Been a Markov Chain Language Model
- Published on
- ∘ ~28 mins ∘ ––– views
Reject modernity (transformers); embrace tradition (markov chains)- Sutton, Barto, Bhoag
- This text was generated by a rnn with 700 hidden nodes across 4 layers trained on everything I've has ever written over 500 epochs
14 | ML 3: A Summary of a Summary: DQN Bottlenecks
- Published on
- ∘ ~5 mins ∘ ––– views
RL + Sergey Levine + Swords!11 | ML 2: A Discussion of Action Spaces
- Published on
- ∘ ~3 mins ∘ ––– views
Just dumb enough that it might work10 | ML 1: Reinforcement Learning, So Hot Right Now
- Published on
- ∘ ~12 mins ∘ ––– views
Overview of a Summary of Reinforcement Learning