Notes
Course Notes
- CS285 (incomplete): Deep Reinforcement Learning
- CS182: Designing, Visualizing and Understanding Deep Neural Networks
- EECS126: Probability and Random Processes
Math Notes
- Block Matrix Inverse and Woodbury Formula: In this note, I go into the proof of the block-wise matrix inverse and Woodbury Formula.
- Marginal and Conditional Distributions of Multivariate Gaussians: In this note, I use the block-wise matrix inverse and Woodbury Formula to derive the marginal and conditional distributions of multivariate gaussians.
- Determinants: In this note, I develop the definition of determinants from multilinearity and use this definition to derive its permutation definition, cofactor expansion, and various other determinant properties.
- Equivalence of Jointly Gaussian Random Vector Definitions: In this note, I prove the equivalence of the multiple different definitions of jointly Gaussian random vectors and go into some misconceptions regarding them.
ML Notes
- Unsupervised Learning: Notes on unsupervised learning papers. Includes VAE, VQVAE, VIB.
Book Notes
- Lifespan: Why We Age―and Why We Don't Have To: Notes on Harvard Professor David Sinclair's book on aging.