High Fidelity Simulations: The Critical Path to Real-World AI
320 views · Published 9 May 2018 · 18:19 · Indexed 12 November 2026
Channel: Microsoft Developer · 2018 · People & Blogs
Developing and testing real-world AI is an expensive and time consuming process. Machine Learning is one of the key component that enables these systems to operate under uncertainty. However, in order to utilize recent advances in machine intelligence and deep learning we need to collect a large amount of annotated training data in a variety of conditions and environments. Also, such data driven system are far from perfect and can result in failure cases that can jeopardize safety. In this session we will explore how high fidelity simulations can help us alleviate some of these problems. We will discuss how such near-realistic simulations can help not only with gathering training but also can be embedded in imitation-learning or reinforcement learning loops in order to improve sample complexity. Our discussion will center around AirSim, an open-source simulator built on Unreal Engine that offers physically and visually realistic simulations.
More from this channel
-
32:36
Episode 2: Germany - Interview with Dominick Baier
-
44:56
Episode 3: England - Interview with Evelina Gabasova
-
14:12
TWC9: Connect(); Next Week, Picking the Right Azure VM, Star Wars Video Cards and more...
-
14:41
TWC9: Connect(); On-Demand, Dev’s Guide to Azure, Future Workspace, Furby Hacking and more...
-
45:16
The Xamarin Show | Episode 1: Sharing Code Across iOS, Android, and Windows
-
20:24
Interview with Harini Gupta, Senior Program Manager at Microsoft
-
19:55
Announcing General Availability of Azure Bot Service and Language Understanding service
-
18:59
Meet the new Azure IoT Remote Monitoring Preconfigured Solution