-
Quantization for Neural Networks
how to properly quantize neural networks for efficient hardware inference?
-
Enforcing Lipschitz Constant in Neural Network
how to enforce lipschitz constraint in neural networks?
-
Langevin Dynamics for Bayesian Inference
stochastic differential equation, Fokker Plank equation, and their connections to Bayesian inference
-
Understanding and Implementing Asymmetric Numeral System (ANS)
an introduction of ANS and its implementation
-
Arithmetic Coding (AC) Implementation
python implementation of arithmetic coding
-
Optical Flow -- An Overview
summary of how optimal flow can be derived
-
Markov Chain Monte Carlo: Gibbs, Metropolis-Hasting, and Hamiltonian
a primer on Gibbs sampling, Metropolis-Hasting, and Hamiltonian MC
-
Normalizing Flow: understanding the change of variable equation
decipher absolute-logarithm-determinant-Jocabian
-
Understanding conventional HMM-based ASR training
call me an archeologist
-
Comparison of end-to-end ASR models
how CTC, RNN-transducer, and Attention factor probabilities
-
Gumbel max and Gumbel softmax
sampling of softmax == max of (logit + Gumbel noise)
-
An introduction to Kalman filter and particle filter
Kalman filter 101
-
Griffin-Lim algorithm for waveform reconstruction
the age before neural vocoder
-
A step-by-step guide to variational inference (4): variational auto encoder
learned amortized posterior == encoder
-
A step-by-step guide to variational inference (3): mean field approximation
posterior approximation before age of deep learning
-
A step-by-step guide to variational inference (2): expectation maximization
how to optimize ELBO when your approx posterior can be easily obtained
-
A step-by-step guide to variational inference (1): variational lower bound
what is variational lower bound, why it is important, and how to derive it
-
A solution manual to the Elements of Statistical Learning (ESL)
my solution to selected problems