posts on machine learning, statistics, opinions on things I'm reading in the space
Everything that Works Works Because it's Bayesian: Why Deep Nets Generalize?
May 25th, 2017
Exemplar CNNs and Information Maximization
May 11th, 2017
Is Maximum Likelihood Useful for Representation Learning?
May 4th, 2017
Unsupervised Learning by Predicting Noise: an Information Maximization View
April 21st, 2017
Evolution Strategies, Variational Optimisation and Natural ES
April 6th, 2017
Evolution Strategies: Almost Embarrassingly Parallel Optimization
March 30th, 2017
Choice of Recognition Models in VAEs: a regularisation view.
March 28th, 2017
Comment on "Overcoming catastrophic forgetting in NNs": Are multiple penalties needed?
March 16th, 2017
The Spherical Kernel Divergence
March 9th, 2017
Variational Inference using Implicit Models
February 28th, 2017
Page 1 of 7