A while back I an­swered a ques­tion on Quora: Can peo­ple ac­tu­al­ly keep up with note-​taking in Math­e­mat­ics lec­tures with LaTeX. There, I ex­plained my work­flow of tak­ing lec­ture notes in LaTeX using Vim and how I draw fig­ures in Inkscape. How­ev­er, a lot has changed since then and I’d like to write a few blog posts ex­plain­ing my work­flow.

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 the perspective of deep learning, robotics, AGI, neuroscience, philosophy, psychology, cognitive science, economics, physics, mathematics, and more.

If you’re reading papers, you should know how to pronounce the greek letters. Here’s a helpful memory aid for that task.

The recurrent weights are not modeled as a full matrix, but as a diagonal matrix… consistently outperform regular LSTMs both in terms of accuracy per parameter, and in best accuracy overall

They measure how stiff a network is by looking at how a small gradient step on one example affects the loss on another. Stiffness is useful for diagnosing and characterizing generalization.

GluonCV provides implementations of the state-of-the-art (SOTA) deep learning models in computer vision.

It is designed for engineers, researchers, and students to fast prototype products and research ideas based on these models. This toolkit offers four main features:

Training scripts to reproduce SOTA results reported in research papers A large number of pre-trained models Carefully designed APIs that greatly reduce the implementation complexity Community supports

One of the biggest bottlenecks in developing machine learning (ML) applications is the need for the large, labeled datasets used to train modern ML models. Creating these datasets involves the investment of significant time and expense, requiring annotators with the right expertise. Moreover, due to the evolution of real-world applications, labeled datasets often need to be thrown out or re-labeled.

https://ai.googleblog.com/2019/03/harnessing-organizational-knowledge-for.html

Use our knowledge from the fields of Computer Vision, Deep Reinforcement Learning and Game Development to create a functional simulation of our robot, G.E.A.R - Garbage Evaporating Autonomous Robot. This blog post presents the details of the endeavour.

We will see how HRL can be an attractive way to counter the limits of RL, including its motivations, main frameworks and own limitations. Finally, we will discuss active and future research in this area.

Achieving a research-level understanding of most topics is like climbing a mountain. Aspiring researchers must struggle to understand vast bodies of work that came before them, to learn techniques, and to gain intuition. Upon reaching the top, the new researcher begins doing novel work, throwing new stones onto the top of the mountain and making it a little taller for whoever comes next.