In Lecture 14 we move from supervised learning to reinforcement learning (RL), in which an agent must learn to interact with an environment in order to maximize its reward. We formalize reinforcement learning using the language of Markov Decision Processes…

EE380: Computer Systems Colloquium
HPC Opportunities in Deep Learning
Speaker: Greg Diamos, Baidu

Just this year, deep learning has fueled significant progress in computer vision, speech recognition, and natural language processing. We have seen a computer…

Стартап курс CS183 - Стэнфорд, весна 2012 г. читать онлайн. Весной 2012 года в Стенфордском университете Питер Тиль Peter Thiel провел курс Стартап. Перед началом первой лекции Питер заявил

The unexpected outbreak of COVID-19 has such huge influence that it has developed into a public health emergency of international concern (PHEIC). According to the statistics up to February 16 at 19:00, there were a total of 69285 confirmed cases globally…

MS&E 476: Entrepreneurship through the Lens of Venture Capital

Ernestine Fu is an angel investor in Silicon Valley, partner at venture capital firm Alsop Louie Partners, and instructor at Stanford University.

In this talk, Ernestine discusses the foundations…

Contextual embeddings have revolutionized NLP, but are highly computationally expensive. In this work we focus on the question of when contextual embeddings are worth their cost, versus when it is possible to use more efficient word representations without…

The stochastic multi-armed bandit (MAB) is a benchmark model for decision-making under uncertainty. MABs are used in a wide range of applications, from Internet advertising to healthcare. Now, new research has suggested that algorithms for MAB problems that…