We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever ‘stale’), making it conceptually simple and easy to implement.
Honored to be invited as the keynote/guest speaker at the Spine Summit 2020, The 36th Annual Meeting of the American Association of Neurological Surgeons (AANS) and the Congress of Neurological Surgeons (CNS) on March 6, 2020, at the Cosmopolitan of Las Vegas, in Las Vegas, Nevada, USA. Here is the full program of the conference. […]
Abstract We propose 4 insights that help to significantly improve the performance of deep learning models that predict surface normals and semantic labels from a single RGB image. These insights are: (1) denoise the ”ground truth” surface normals in the training set to ensure consistency with the semantic labels; (2) concurrently train on a mix […]
It is great to see someone who has done so much for Computational Journalism, continue to support it this way. Thanks Krishna Bharat. Friday, November 1, 2019The creator of Google News has endowed a new faculty chair position in computational journalism at Georgia Tech’s College of Computing. Krishna Bharat – Georgia Tech alumnus (MS CS […]
It was great to host Jeff Dean during his recent visit to Georgia Tech It’s not every day that Google’s head of artificial intelligence visits Georgia Tech, but when he does he makes an impact. Hosted by the College of Computing and the Machine Learning Center (ML@GT), Jeff Dean, senior fellow and senior vice president […]
Abstract To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task – Embodied Question Answering in photo-realistic environments (Matterport 3D). We thoroughly study navigation policies that utilize 3D point clouds, RGB images, or their combination. Our analysis of these models reveals several […]
Abstract We introduce the task of scene-aware dialog. Our goal is to generate a complete and natural response to a question about a scene, given video and audio of the scene and the history of previous turns in the dialog. To answer successfully, agents must ground concepts from the question in the video while leveraging […]
