Basic ideas behind optimization on non-Euclidean manifolds and how it ties to the common problem of doing optimization over Lie Groups in robotics and computer vision

When does it make sense to leave a big tech job for a startup

Can the influential ideas from Kahnemann and others' research about humans having two modes of thinking, one fast, one slow, be applied to current machine learning systems

Collection of some recent work on uncertainty estimation for deep learning models using Bayesian and non-Bayesian methods

An introduction and comparison of two popular techniques for estimating gradients in machine learning models

Highlighting ideas at the intersection of cognitive science and machine learning by summarizing the work of Lake et al (2016) and its related paper commentaries

How can we define what an interpretable model is and why is it even an important question to ask

Exploring the relationship between variational inference and expectation maximization algorithm