Exploiting T-norms for Deep Learning in Autonomous Driving

arXiv:2402.11362v1 Announce Type: new
Abstract: Deep learning has been at the core of the autonomous driving field development, due to the neural networks' success in finding patterns in raw data and turning them into accurate predictions. Moreover, recent neuro-symbolic works have shown that incorporating the available background knowledge about the problem at hand in the loss function via t-norms can further improve the deep learning models' performance. However, t-norm-based losses may have very high memory requirements and, thus, they may …

abstract arxiv autonomous autonomous driving core cs.cv cs.lg cs.lo data deep learning development driving knowledge networks neural networks neuro patterns predictions raw success them type