PAIR is devoted to advancing the research and design of people-centric AI systems.
We're interested in the full spectrum of human interaction with machine intelligence, from supporting engineers to understanding everyday experiences with AI. Our goal is to do fundamental research, invent new technology, and create frameworks for design in order to drive a humanistic approach to artificial intelligence. And we want to be as open as possible: we’re building open source tools that everyone can use, hosting public events, and supporting academics in advancing the state of the art.
Deeplearn.js is an open-source library for hardware-accelerated machine learning on the web. Train neural nets entirely in your browser, or run pre-trained models.
A new technique for improving saliency/sensitivity maps called SmoothGrad, developed by the Big Picture team. The SmoothGrad technique often significantly denoises sensitivity masks. This technique adds pixel-wise Gaussian noise to many copies of the image, and simply averages the resulting gradients.
Facets contains two robust visualizations to aid in understanding and analyzing machine learning datasets, to help researchers build better and more powerful machine learning systems. Get a sense of the shape of each feature of your dataset using Facets Overview, or explore individual observations using Facets Dive.