6 papers
DB-KSVD: Scalable Alternating Optimization for Disentangling High-Dimensional Embedding Spaces
Romeo Valentin, Sydney M. Katz, Vincent Vanhoucke +1
Dictionary learning has recently emerged as a promising approach for mechanistic interpretability of large transformer models. Disentangling high-dimensional transformer embeddings…
The FABRIC Strategy for Verifying Neural Feedback Systems
Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer +1
Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and…
A New Strategy for Verifying Reach-Avoid Specifications in Neural Feedback Systems
Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer +1
Forward reachability analysis is the predominant approach for verifying reach-avoid properties in neural feedback systems (dynamical systems controlled by neural networks). This do…
Aircraft Collision Avoidance Systems: Technological Challenges and Solutions on the Path to Regulatory Acceptance
Sydney M. Katz, Robert J. Moss, Dylan M. Asmar +3
Aircraft collision avoidance systems is critical to modern aviation. These systems are designed to predict potential collisions between aircraft and recommend appropriate avoidance…
Predictive Uncertainty for Runtime Assurance of a Real-Time Computer Vision-Based Landing System
Romeo Valentin, Sydney M. Katz, Artur B. Carneiro +2
Recent advances in data-driven computer vision have enabled robust autonomous navigation capabilities for civil aviation, including automated landing and runway detection. However,…
Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals
Harrison Delecki, Sydney M. Katz, Mykel J. Kochenderfer
Estimating the probability of failure is a critical step in developing safety-critical autonomous systems. Direct estimation methods such as Monte Carlo sampling are often impracti…