Posted by Quoc Le & Barret Zoph, Research Scientists, Google Brain team At Google, we have successfully applied deep learning models to ma... (more…)

We analyze the type of learned optimization that occurs when a learned model (such as a neural network) is itself an optimizer - a situation we refer to as mesa-optimization, a neologism we introduce in this paper. We believe that the possibility of mesa-... (more…)

If you liked this, back the crowdfunding project: indiegogo.com/projects/neural-networks-for-hackers-education/x/12932257#/ Original paper: https://arxiv.org... (more…)

While debate drags on about legislation, regulations, and other measures to improve the U.S. health care system, a new wave of analytics and technology could help dramatically cut costly and unnecessary hospitalizations while improving outcomes for patien... (more…)

If you’re like me, you’ve heard a lot about Gradient Descent. You’ve heard that it is a foundational algorithm for optimising functions which all self respecting Machine Learning techniques employ … (more…)