We’ve used novel machine learning and tracking architectures to develop a new, fully articulated hand-tracking system for VR.

A game theoretic approach to explain the output of any machine learning model. - shap/shap

Share your videos with friends, family, and the world

❤️ Check out Weights & Biases here and sign up for a free demo: https://www.wandb.com/papers

Weights & Biases blog post (the notebook is available too!)
- https://www.wandb.com/articles/visualize-xgboost-in-one-line
- https://colab.research.google.com/d…

Probability for Machine Learning Crash Course. Get on top of the probability used in machine learning in 7 days. Probability is a field of mathematics that is universally agreed to be the bedrock for machine learning. Although probability is a large field…

We are releasing a new benchmark and dataset to evaluate performance across various neural code search techniques to make it easier to evaluate a new model on a common set of questions.

Decisions based on machine learning (ML) are potentially advantageous over human decisions, as they do not suffer from the same subjectivity, and can be more accurate and easier to analyse. At the same time, data used to train ML systems often contain human…

We are open-sourcing Detectron2, the second-generation of our widely used object-recognition platform. Detectron2 has been rewritten from the ground up in PyTorch to enable faster model iteration and deployment.

The mere idea of AI-synthesized media is already making people stop believing that real things are real

Since deep learning regained prominence in 2012, many machine learning frameworks have clamored to become the new favorite among researchers and industry practitioners. From the early academic outputs Caffe and Theano to the massive industry-backed PyTorch…

We’re open-sourcing a new platform for experimenting with reinforcement learning to proactively adapt to changing traffic patterns.

An AI team at the University of Waterloo, Canada, developed a new type of compact family of deep neural networks (AttoNets), which can even run on smartphones, tablets, and other mobile devices. The main problem with available neural networks is they require…

Recently, Facebook AI has advanced state-of-the-art results in key language understanding tasks and also launched a new benchmark to push AI systems further

❤️ Check out Lambda here and sign up for their GPU Cloud: https://lambdalabs.com/papers

📝 The paper "Learning Predict-and-Simulate Policies From Unorganized Human Motion Data" is available here:
https://mrl.snu.ac.kr/publications/ProjectICC/ICC.html

🙏 We…

Code available: https://github.com/MIT-SPARK/Kimera
Paper: https://arxiv.org/abs/1910.02490

Kimera has also been used in:
- 3D Dynamic Scene Graphs:
Video: https://www.youtube.com/watch?v=SWbofjhyPzI&feature=youtu.be
Paper: https://arxiv.org/abs/2002.06289…