Episode
11/30/24: LB4TL: A Smooth Semantics for Temporal Logic to Train Neural Feedback Controllers with Navid Hashemi
- Podcast
- Boston Computation Club
- Published
- Dec 1, 2024
- Duration seconds
- 2707
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/boston-computation-club-4031660/episodes/11-30-24-lb4tl-a-smooth-semantics-for-temporal-logic-to-train-neural-feedback-controllers-with-navid-hashemi/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/boston-computation-club-4031660/11-30-24-lb4tl-a-smooth-semantics-for-temporal-logic-to-train-neural-feedback-controllers-with-navid-hashemi.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
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.