This tutorial will look at how deep learning methods can be applied to problems in computer vision, most notably object recognition. It will start by motivating the need to learn features, rather than hand-craft them. It will then introduce several basic architectures, explaining how they learn features...

This course is designed to provide participants with an overall understanding of how sex and gender impact function of select organ systems as well as disease progression and treatment options.

Welcome to the world’s first online course in science journalism, developed by the World Federation of Science Journalists in close cooperation with the Science and Development Network SciDev.Net. The course is ready for use by professional journalists, journalism students and teachers. Each course consist...

This second module, entitled Sex and Gender Differences in Health and Behavior, applies the basic concepts presented in the first course to specific conditions and organ systems where sex and gender differences play a significant role.

This course is designed to give the student a basic scientific understanding of the major physiological differences between the sexes, the influences these differences have on illness and health outcomes, and the implications for policy, medical research, and health care.

Developing high quality distributed systems software is hard; developing high quality reusable distributed systems software is even harder. The principles, methods, and skills required to develop reusable software cannot be learned by generalities. Instead, developers must learn through experience how...

Lectures from the NYU Course on Deep Learning (Spring 2014) This is a graduate course on deep learning, one of the hottest topics in machine learning and AI at the moment. In the last two or three years, Deep learning has revolutionized speech recognition and image recognition. Deep learning is...

This is an introductory course by Caltech Professor Yaser Abu-Mostafa on machine learning that covers the basic theory, algorithms, and applications. Machine learning (ML) enables computational systems to adaptively improve their performance with experience accumulated from the observed data. ML techniques...

Modern theoretical methods used in study of molecular structure, bonding, and reactivity. Concepts and practical applications. Semiempirical, ab initio, and density functional calculations of molecular electronic structure. Theoretical determination of molecular structure and spectra; relationship to...

The C++ Grandmaster Certification is an online course in which participants develop their own complete standalone C++ toolchain - including a preprocessor, compiler, assembler, linker, and standard library. The toolchain will produce executable applications for a target of (a) the Linux operating...

Haskell is a high-level, pure functional programming language with a strong static type system and elegant mathematical underpinnings, and is being increasingly used in industry by organizations such as Facebook, AT&T, and NASA. In the first 3/4 of the course, we will explore the joys of pure, lazy,...

A lecture series covering contemporary areas in genomics and bioinformatics. The scientific community celebrated the achievement of the Human Genome Project's major goal in April of 2003: completion of a high-accuracy sequence of the human genome. The significance of this milestone cannot be underestimated...

A lecture series covering contemporary areas in genomics and bioinformatics. The scientific community celebrated the achievement of the Human Genome Project's major goal in April of 2003: completion of a high-accuracy sequence of the human genome. The significance of this milestone cannot be underestimated...

These are the videos I use to teach my Neural networks class at Université de Sherbrooke

Machine learning is a powerful set of techniques that allow computers to learn from data rather than having a human expert program a behavior by hand. Neural networks are a class of machine learning algorithm originally inspired by the brain, but which have recently have seen a lot of success at practical...

Deep Reinforcement Learning

Advanced Topics 2015 (COMPM050/COMPGI13): Reinforcement Learning

Our 4-week advanced course considers how to design interactions between agents in order to achieve good social outcomes. The course -- which is free and open to the public -- considers three main topics: social choice theory (i.e., collective decision making), mechanism design, and auctions. More...

Advanced Topics in Machine Learning: COMPGI13 (kernel part)

A course taught in 2015 at Oxford University with the help of Brendan Shillingford. The course focuses on the exciting field of deep learning. By drawing inspiration from neuroscience and statistics, it introduces the basic background on neural networks, back propagation, Boltzmann machines, autoencoders...