I discuss what counts as strong evidence for an explanation of model behavior.
Nothing in Deep Learning Makes Sense Except in the Light of SGD.
A petty rant on the exceptional treatment of computer vision applications, directed at the machine learning community.
In August of 2015, my hands stopped working. This is what happened next.
Notes on incrementally constraining the architecture of a neural network as a method of regularization.
An explanation of Latent Dirichlet Allocation (LDA), a common method of topic modeling.