"Comparing autonomous driving algorithms with the human drivers" - Kaylene Stocking, YRSS

Originally presented on: Wednesday, October 23rd, 2024 at 11:00am CT, TTIC, 6045 S. Kenwood Avenue, 5th Floor, Room 530
Title: "Comparing deep learning-based autonomous driving algorithms with the brain activity of human drivers"
Speaker: Kaylene Stocking, UC Berkeley
Abstract: Understanding how cognition and learned representations give rise to intelligent behavior is a fundamental goal in both machine learning and neuroscience. However, in both domains, the most well-understood behaviors are passive and open-loop, such as image recognition or speech processing. In this work, we compare human brain activity measured via functional magnetic resonance imaging with deep neural network (DNN) activations for an active taxi-driving task in a naturalistic simulated environment. To do so, we used DNN activations to build voxelwise encoding models for brain activity. Results show that encoding models for DNN activations explain significant amounts of variance in brain activity across many regions of the brain. Furthermore, each functional module in the DNN explains brain activity in a distinct network of functional regions in the brain. The functions of each DNN module correspond well to the known functional properties of its corresponding brain regions, suggesting that both the DNN and the human brain may partition the task in a similar manner. These results represent a first step towards understanding how humans and current deep learning methods agree or differ in active closed-loop tasks such as driving.
Bio: Kaylene is a PhD candidate in electrical engineering and computer sciences at UC Berkeley, advised by Claire Tomlin and working at the intersection of robotics, machine learning, and cognitive science. She is especially interested in general principles that make intelligent behavior possible across both machine and biological systems. Her research has been supported by the Berkeley Fellowship and the Kavli Ethics, Science, and the Public Graduate Fellowship.
#deeplearning #autonomousdriving #algorithm #artificialintelligence #machinelearning #computervision #robotics #research