Deep Learning for Vehicle Perception at Scale
November 6th, Las Vegas
a tutorial at IEEE-Intelligent Vehicle Symposium 2020
a tutorial at IEEE-Intelligent Vehicle Symposium 2020
Jose M. Alvarez (Senior Research Manager / Principal Scientist)
Nicolas Koumchatzky (Director AI Infrastructure)
Nicolas Koumchatzky is a Director of AI Infrastructure at NVIDIA. He is currently managing an organization building a cloud AI platform to power the development of Autonomous Vehicles. Previously, he was managing Twitter’s centralized AI Platform team Twitter Cortex.
Jose M. Alvarez (Senior Research Manager / Principal Scientist)
Elmar Haussmann (Senior Deep Learning R&D Engineer)
Elmar Haussmann is a senior deep learning engineer at NVIDIA. Previously, he was the CTO at RiseML, a company he co-founded to cope with the challenges of large-scale machine learning. Elmar completed his Ph.D. studies in 2016 in the area of AI and natural language understanding. Elmar also worked as a software engineer at IBM in the area of high-performance infrastructure.
Alperen Degirmenci (Senior Deep Learning R&D Engineer)
Alperen Degirmenci earned his Ph.D. and M.S. degrees in Electrical Engineering from Harvard University in 2018 and 2015 with a secondary field in Computational Science and Engineering, and his B.S. degree in Mechanical Engineering from the Johns Hopkins University in 2012, with minors in mathematics, computer science, robotics, and computer-integrated surgery. Alperen’s research at the Harvard Biorobotics Lab focused on real-time, high-performance algorithm development for medical ultrasound image processing and robotic procedure guidance in catheter-based cardiac interventions. He is currently working on autonomous driving as a Senior Deep Learning R&D Engineer at NVIDIA.
Zongyi Yang ( Deep Learning R&D Engineer)
Zongyi Yang ( Deep Learning R&D Engineer)
Haiguang Wen (Senior Deep Learning R&D Engineer)
Haiguang Wen is a senior Deep Learning R&D engineer in autonomous driving at NVIDIA. His interest is building R&D infrastructure and developing models and algorithms for autonomous driving. He received his Ph.D. degree in 2018 from ECE Department at Purdue University, and his research was about developing brain-inspired deep-learning models for computer vision based on the neuroscience theory and experiments
Maying Shen ( Deep Learning R&D Engineer)
Deep learning is a fundamental part for vehicle perception. Obtaining production ready networks to be deployed in safety critical systems involves developing the full learning stack: from data acquisition and labeling to deployment in the edge passing through the tedious task of actually training the network. In this tutorial, we cover the topics needed to produce perception for autonomous driving at scale including topics such as recent advances on active learning and smart data sampling, training and inference efficiency and network robustness.
The tutorial/workshop consists of research talks and technical sessions related to relevant aspects of vehicle perception such as: active learning, efficient training, real-time inference or continual learning among others. Research talks will cover the most advanced details of these topics while during the technical sessions, we aim at providing enough technical details to cover the specific topics in detail and how these techniques can actually be implemented using NVIDIA software / hardware.