Tags: #machine learning

Intuition and derivation of natural gradient descent.

An introduction and intuition of Fisher Information Matrix.

An introduction and implementation of Annealed Importance Sampling (AIS).

Implementation of Gibbs Sampler for the inference of Latent Dirichlet Allocation (LDA)

Training GAN by moving the generated samples to the decision boundary.

2017 is the year GAN loss its logarithm. First, it was Wasserstein GAN, and now, it's LSGAN's turn.

Original GAN and Conditional GAN are for learning marginal and conditional distribution of data respectively. But how can we extend ...

Wasserstein GAN comes with promise to stabilize GAN training and abolish mode collapse problem in GAN.

Adding Mutual Information regularization to a GAN turns out gives us a very nice effect: learning data representation and its ...

We will show that doing MLE is equivalent to minimizing the KL-Divergence between the estimator and the true distribution.