+++ Uber details Fiber, a framework for distributed AI model training +++ Google open-sources framework that helps massively scale RL workloads +++ Rightsizing Neural Nets +++ Generating music in the waveform domain +++

I'm usually writing my notes on physics and mathematics, e.g. the ongoing series of posts on Riemannian geometry, in \(\LaTeX\) documents, as probably most people do. For the purpose of this blog I regularly need to convert parts of these documents into markdown that Hugo can understand. Since I haven't found any better solution yet I decided to develop a set of regular expressions in Python that do the job pretty well. I normally run the code in a Jupyter notebook that allows me to check the quality of conversion immediately and do some minor tweaking if required.

+++ Microsoft, Google and Other Tech Companies Work on AI Ethics +++ Introducing Dreamer: Scalable Reinforcement Learning Using World Models +++

+++ Creators and Core Contributors Talk About 6 High-Level APIs in the PyTorch Ecosystem +++ Satellites and AI Monitor Chinese Economy’s Reaction to Coronavirus +++ Best Practices for Managing and Engineering ML Projects +++ AlphaGo - The Movie +++

+++ Kubeflow 1.0 Brings a Production-Ready Machine Learning Toolset to Kubernetes +++ SciPy 1.0: fundamental algorithms for scientific computing in Python +++ GitLab Handbook +++ Largest gift in Berkeley’s history will create a ‘hub’ for advancing data science +++ Machine Learning with Python +++ Pattern Recognition & Machine Learning algorithms +++

This is a follow-on from a previous post on differentiable manifolds. It is part of a series of posts that I write on the basics of differential or Riemannian geometry, providing the necessary background for reading some of the more advanced textbooks on general relativity. The following posts will cover tensors, covariant derivatives and parallel transport. The presentation will be informal, focusing mostly on motivation, definitions and key facts, not on mathematical proofs.

+++ Powered by AI: Turning any 2D photo into 3D using convolutional neural nets +++ When AI Can’t Replace a Worker, It Watches Them Instead +++ Co-creator of YOLO has turned his back on computer vision over ethical issues +++ Fastai: A Layered API for Deep Learning +++

+++ LinkedIn is open sourcing its metadata search and discovery platform DataHub +++ Google Brain and DeepMind researchers attack reinforcement learning efficiency +++ The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence +++ Scaling Knowledge at Airbnb +++

The Windows Subsystem for Linux (WSL) is a great solution for developers to natively work within Linux right on their Windows 10 version desktop. WSL lets developers run a GNU/Linux environment – including most command-line tools, utilities, and applications – directly on Windows, unmodified, without the overhead of a virtual machine. After some surprisingly super-easy setup, this gives you a truly native POSIX / Unix-like environment directly integrated into your Windows PC, essentially negating a vast majority of issues people had previously with workarounds like dual booting, VMing or terminal wrappers like CYGWIN or Git Bash. According to Microsoft, WSL requires fewer resources (CPU, memory, and storage) than a full virtual machine while also allowing users to use Windows apps and Linux tools on the same set of files. In this article I’m covering some background on WSL and show how to get started.

+++ Five Interesting Data Engineering Projects +++ A new model and dataset for long-range memory +++ Building a Backtesting Service to Measure Model Performance at Uber-scale +++