4 papers
Risk-Based Safety Envelopes for Autonomous Vehicles Under Perception Uncertainty
Julian Bernhard, Patrick Hart, Amit Sahu +2
Ensuring the safety of autonomous vehicles, given the uncertainty in sensing other road users, is an open problem. Moreover, separate safety specifications for perception and plann…
Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning
Alexander Sagel, Amit Sahu, Stefan Matthes +5
Research in machine learning is at a turning point. While supervised deep learning has conquered the field at a breathtaking pace and demonstrated the ability to solve inference pr…
Application of the Neural Network Dependability Kit in Real-World Environments
Amit Sahu, Noelia Vállez, Rosana Rodríguez-Bobada +3
In this paper, we provide a guideline for using the Neural Network Dependability Kit (NNDK) during the development process of NN models, and show how the algorithm is applied in tw…
Survey of reasoning using Neural networks
Amit Sahu
Reason and inference require process as well as memory skills by humans. Neural networks are able to process tasks like image recognition (better than humans) but in memory aspects…