DL2: Training and Querying Neural Networks with Logic

Channel:

Subscribers:

68,700

Published on May 13, 2021 5:21:03 AM ● Video Link: https://www.youtube.com/watch?v=eC5kHuqihnc

Category:

Vlog

Duration: 30:21

715 views

Other Videos By Simons Institute for the Theory of Computing

2021-05-17	On the Formal Characterization of Industrial SAT Instances
2021-05-16	On Using Structural Properties to Improve CDCL Solver Performance
2021-05-16	Towards an (Experimental) Understanding of SAT Solvers
2021-05-16	Perspectives on Practice and Theory of SAT Solving
2021-05-14	Abstract Value Iteration for Hierarchical Reinforcement Learning
2021-05-14	A Negotiation Procedure for Distributed Reactive Synthesis
2021-05-14	Theoretically Speaking — A Panel Discussion on the Film Coded Bias
2021-05-13	On Time, and Space, and Width, and Depth
2021-05-13	A Personal History of Practical SAT Solving
2021-05-12	Constrained Gradient Descent Algorithm for Testing Neural Networks
2021-05-12	DL2: Training and Querying Neural Networks with Logic
2021-05-12	Training Neural Networks with a Little Help from Knowledge
2021-05-12	Unifying Logical and Statistical AI with Markov Logic
2021-05-12	Panel Discussion on Quantum Algorithms for Optimization \| Quantum Colloquium
2021-05-12	Quantum Algorithms for Optimization \| Quantum Colloquium
2021-05-11	The Multilinear Polytope for Acyclic Hypergraphs
2021-05-10	Panel Discussion on Challenges and Opportunities in Synthesis
2021-05-07	Formal Languages and Automata for Reward Function Specification and Efficient Reinforcement Learning
2021-05-07	Avenir: Managing Data Plane Diversity via Control Plane Synthesis
2021-05-06	Cooperative Competition: A New Way of Solving SAT and other NP-Hard Problems in AI and Beyond
2021-05-06	Using Program Synthesis to Build Compilers

Tags:

Simons Institute

theoretical computer science

UC Berkeley

Computer Science

Theory of Computation

Theory of Computing

Marc Fischer

Theoretical Foundations of SAT/SMT Solving