Originally published in infoproc.blogspot.com, Feb 7, 2021. This paper shows that models which result from gradient descent training (e.g., deep neural nets) can be expressed as a weighted sum of similarity functions (kernels) which measure the similarity of a given instance to the examples used in training. The kernels are defined by the inner product
Originally published in MIT Technology Review, Jan 15, 2021. A growing ecosystem of “responsible AI” ventures promise to help organizations monitor and fix their AI models. Rumman Chowdhury’s job used to involve a lot of translation. As...
Why pretrained machine learning models are often unusable and irreproducible — and what we can do about it. Introduction A useful approach to designing software is through contracts. For every function in your codebase, you start by writing...
Originally published in [email protected], Jan 19, 2021. When Facebook users scroll through their News Feed, they find all kinds of content — articles, friends’ comments, event invitations, and of course, photos. Most people are able to instantly...
Originally published in Chip Huyen, Dec 27, 2020. After talking to machine learning and infrastructure engineers at major Internet companies across the US, Europe, and China, I noticed two groups of companies. One group has made significant...
Originally published in The Netflix Tech Blog, Dec 10, 2020. Netflix is pioneering content creation at an unprecedented scale. Our catalog of thousands of films and series caters to 195M+ members in over 190 countries who span...
Originally published in Facebook AI, Dec 11, 2020. AI has made progress in detecting hate speech, but important and difficult technical challenges remain. Back in May 2020, Facebook AI partnered with Getty Images and DrivenData to launch...
