Despite its ubiquity in deep learning, Tensor is broken. It forces bad habits such as exposing private dimensions, broadcasting based on absolute position, and keeping type information in documentation. This post presents a proof-of-concept of an alternative approach, named tensors, with named dimensions. This change eliminates the need for indexing, dim arguments, einsum- style unpacking, and documentation-based coding.

New textbook by Gilbert Strang, “Linear Algebra and Learning from Data”, coming January 2019, includes #deeplearning ⁦

Looking for papers with code? If so, this GitHub repository, a clearinghouse for research papers and their corresponding implementation code, is definitely worth checking out.

Best paper awards in computer science since 1996. Updated for 2018. https://t.co/Cc7mvxdpjc

GitHub is one of the most popular sources and this year GitHub featured a lot of open source projects. It also saw a record number of new users coming to GitHub and hosted over 100 million repositories. While there have been a lot of projects, there were a few that grabbed more popularity than the others. In this article, we list the top 10 open source projects by unique contributors that were used the most, which is largely decided by the number of stars received by the projects.

A visual introduction to probability and statistics: https://t.co/X20Xb8VPgO - The visualizations here are amazing

The Artificial Intelligence (AI) podcast hosts accessible, big-picture conversations at MIT and beyond about the nature of intelligence with some of the most interesting people in the world thinking about AI from a variety of perspectives including machine learning, robotics, neuroscience, philosophy, psychology, economics, physics, mathematics, cognitive science, software engineering and more.

If I had to summarize the main highlights of machine learning advances in 2018 in a few headlines, these are the ones that I would probably come up:

• AI hype and fear mongering cools down
• More focus on concrete issues like fairness, interpretability, or causality
• Deep learning is here to stay and is useful in practice for more than image classification (particularly for NLP)
• The battle on the AI frameworks front is heating up, and if you want to be someone you better publish a few frameworks of your own

This page is a collection of MIT courses and lectures on deep learning, deep reinforcement learning, autonomous vehicles, and artificial intelligence taught by Lex Fridman.

How Facebook Implements Speech Recognition Systems Completely Based on Convolutional Neural Networks

• Paper
• Github