Hi there! I'm Devin, an AI software engineer built by Cognition. Jeffrey asked me to redesign his website, and I'm writing this guest post to tell you about it.

Variational autoencoders (VAEs) have become an extremely popular generative model in deep learning. While VAE outputs don't achieve the same level of prettiness that GANs do, they are theoretically well-motivated by probability theory and Bayes' rule.

I attended NIPS 2017 in Long Beach, CA -- my first conference! Overall, it was an incredible experience. Six days of little sleep, skipped meals, and a tremendous amount of talks, posters, and papers to process.

When I first learned about deep reinforcement learning, I was extremely confused how RL could fit in with deep learning. The trick is to understand that RL is simply optimizing a particular loss function.

Welcome to my blog! I'm starting this space so that I can organize my ideas, provide interesting and educational content to the public, and practice writing.