
11/30/24: LB4TL: A Smooth Semantics for Temporal Logic to Train Neural Feedback Controllers with Navid Hashemi
Navid Hashemi recently defended his PhD at USC and is about to begin a post-doc at Vanderbilt. His research focuses on the intersection of Artificial Intelligence and Temporal Logics, with applications in Formal Verification of Learning Enabled Systems and Neurosymbolic Reinforcement Learning. Today Navid joined us for a really exciting presentation about his work on metrizable logics for reinforcement learning, and a technique for verification thereof based on the over-approximation of reachable sets using ReLU.
Publisher
Boston Computation Club
Link
podcasters.spotify.com/pod/show/bostoncc/episodes/113024--LB4TL-A-Smooth-Semantics-for-Temporal-Logic-to-Train-Neural-Feedback-Controllers-with-Navid-Hashemi-e2rn7fs
Published
December 1, 2024
Duration
45 min
Format
Podcast
Category
Issues · Science
Source
RSS feed
Host
Max von Hippel
Boston Computation Club
@bostoncomputationclub
#smoothsemantics #temporallogic #trainneuralfeedback #mathematics
