all AI news
Provably Safe Neural Network Controllers via Differential Dynamic Logic
Feb. 20, 2024, 5:43 a.m. | Samuel Teuber, Stefan Mitsch, Andr\'e Platzer
cs.LG updates on arXiv.org arxiv.org
Abstract: While neural networks (NNs) have a large potential as goal-oriented controllers for Cyber-Physical Systems, verifying the safety of neural network based control systems (NNCSs) poses significant challenges for the practical use of NNs -- especially when safety is needed for unbounded time horizons. One reason for this is the intractability of NN and hybrid system analysis. We introduce VerSAILLE (Verifiably Safe AI via Logically Linked Envelopes): The first approach for the combination of differential dynamic …
abstract arxiv challenges control control systems cs.ai cs.lg cs.lo cs.sy cyber differential dynamic logic network networks neural network neural networks nns practical reason safety systems type via
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)
@ HelloBetter | Remote
Doctoral Researcher (m/f/div) in Automated Processing of Bioimages
@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Real World Evidence Research Analyst
@ Novartis | Dublin (Novartis Global Service Center (NGSC))
Senior DataOps Engineer
@ Winterthur Gas & Diesel AG | Winterthur, CH