Volkswagen : When changing the environment or the sensor technology, neural networks in vehicles today have to be trained again and again from scratch. ...
October 08, 2021 at 05:12 am EDT
Share
This kind of learning gobbles up enormous resources. "Today, it takes 70,000 graphics processor hours to train an autopilot," explains Tobias Kalb, a doctoral student involved in the AI Delta Learning project for Porsche Engineering. In practice, numerous graphics processing units (GPUs) are used in parallel to train neural networks, but the effort is still considerable. In addition, a neural network needs annotated images, that is images from real traffic events in which important elements are marked, such as other vehicles, lane markings, or crash barriers. If a human performs this work manually, it takes an hour or more to annotate a snapshot from city traffic. Every pedestrian, every single zebra crossing, every construction site cone must be marked in the image. This labelling, as it is known, can be partially automated, but it requires large computing capacities.
In addition, a neural network sometimes forgets what it has learned when it has to adapt to a new domain. "It lacks a real memory," explains Kalb. He himself experienced this effect when using an AI module trained with US traffic scenes. It had seen many images of empty highways and vast horizons and could reliably identify the sky. When Kalb additionally trained the model with a German dataset, a problem arose. After the second run, the neural network had trouble identifying the sky in the American images. In the German images, it was it was often cloudy or buildings blocked the view.
Attachments
Original document
Permalink
Disclaimer
Volkswagen AG published this content on 08 October 2021 and is solely responsible for the information contained therein. Distributed by Public, unedited and unaltered, on 08 October 2021 09:01:08 UTC.
Volkswagen AG is a Germany-based Company, which manufactures and sells vehicles. The Company operates through four segments: Passenger Cars, which covers the development of vehicles and engines, the production and sale of passenger cars, and the corresponding genuine parts business; Commercial vehicles, which comprises the development, production and sale of light commercial vehicles, trucks and buses, the genuine parts business and related services; Power Engineering, which consists of the development and production of diesel engines, turbo compressors, industrial turbines and chemical reactor systems, the production of gear units, propulsion components and testing systems, and Financial Services, which comprises dealer and customer financing, leasing, banking and insurance activities, fleet management and mobility services. It's brand portfolio includes Volkswagen, Audi, SEAT, SKODA, Bentley, Bugatti, Lamborghini, Porsche, Ducati, Volkswagen Commercial Vehicles, Scania and MAN.
Volkswagen : When changing the environment or the sensor technology, neural networks in vehicles today have to be trained again and again from scratch. ...