Undirected graphical models formed a large part of the initial push for machine intelligence, and remain relevant today. Here, I motivate and derive Monte Carlo-based learning algorithms for such models.

1

We motivate and derive the generalized backpropagation algorithm for arbitrarily structured networks.

2

We discuss the fundamental ideas behind fully convolutional networks, including the transformation of fully connected layers to convolutional layers and upsampling via transposed convolutions ("deconvolutions").

3

We motivate and derive the backpropagation learning algorithm for convolutional networks.

4

We motivate and derive the backpropagation learning algorithm for feedforward networks.

5

A detailed look at one of my favorite software security papers, and its implications on bootstrapping trust.

6

Directed latent variable models provide a powerful way to represent complex distributions by combining simple ones. However, they often have intractable log-likelihoods, yielding complicated learning algorithms. In this post, we build intuition for these concepts.

7