A few QA’s from the course F’20 <Deep Learning>

i’ve just finished teaching <Deep Learning> this semester together with Yann and Alfredo. the course was in a “blended mode”, implying that lectures were given in person and live-streamed with a limited subset of students allowed to join each week and all the other students joining remotely via Zoom. this has resulted in more active online discussion among students, instructors and assistants over the course, and indeed there were quite a few interesting questions posted on the course page which was run on campuswire. i enjoyed answering those questions, because they made me think quite a bit about them myself.

Scaling laws of recovering Bernoulli

[Initial posting on Nov 29 2020][Updated on Nov 30 2020] added a section about the scaling law w.r.t. the model size, per request from Felix Hill. [Updated on Dec 1 2020] added a paragraph referring to Dauphin & Bengio’s “Big Neural Networks Waste Capacity“.{Update on Feb 8 2021] see “Learning Curve Theory” by Marcus Hutter for a better exposition of the scaling law and where it might be coming from. this is a short post on why i thought (or more like imagined) the scaling laws from <scaling laws for autoregressive generative modeling> by Heninghan et al. “[is] inevitable from

Giving thanks: Samsung AI Researcher of the Year Award and Donation to Mila

Note: see this announcement on the Mila’s homepage Earlier this month (Nov 2020) at the Samsung AI Forum 2020 I was one of the five recipients of the inaugural Samsung AI Researcher of the Year Award by the Samsung Advanced Institute of Technology (SAIT). Samsung has been supporting my research ever since I was a postdoc at Mila in Montreal, and without their support I wouldn’t have been able to support all my PhD students (NSF, i’m looking at you!) Because of this prolonged support, I had been already grateful to Samsung even before this award, and I am even

A foreword written for the K-12 AI education material <콕!찝!AI> by Busan Metropolitan City Office of Education

Click here to jump to my foreword and skip the background. If you want to read the foreword in pdf, click here. If you’re interested in the tables of contents from the series, click here. Here’s my video message for their publication celebration: Background: Right before COVID-19 struck NY heavily this past Spring, K-12 teachers from Busan, Korea stopped by at NYC on their trip to US for studying various AI education strategies in US, and asked me for a short meeting. Frankly i was quite skeptical about this meeting, and was assuming it was their vacation in disguise.

Creating an encyclopedia from GPT-3 using B̶a̶y̶e̶s̶’̶ ̶R̶u̶l̶e̶ Gibbs sampling

[WARNING: there is nothing “WOW” nor technical about this post, but a piece of thought i had about GPT-3 and few-shot learning.] Many aspects of OpenAI’s GPT-3 have fascinated and continue to fascinate people, including myself. these aspects include the sheer scale, both in terms of the number of parameters, the amount of compute and the size of data, the amazing infrastructure technology that has enabled training this massive model, etc. of course, among all these fascinating aspects, meta-learning, or few-shot learning, seems to be the one that fascinates people most. the idea behind this observation of GPT-3 as a