My Blog

blog posts about topics in deep learning, statistics and AI safety

Post-Hoc Approaches to Interpreting Reinforcement Learning Agents

9 min read · September 01, 2024

2024 · deep-learning, rl, interpretability
A Very Brief Investigation of Using Finetuning To Interpret Wav2Vec 2.0

10 min read · August 20, 2024

2024 · deep-learning, asr, interpretability
Basic MCMC Pt. 2: The Metropolis-Hastings Algorithm

21 min read · February 09, 2024

2024 · mcmc, statistics
Bandit Algorithms (& The Exploration-Exploitation Tradeoff)

26 min read · January 24, 2024

2024 · rl
Variational Dropout in Recurrent Models

12 min read · January 16, 2024

2024 · deep-learning