Search Results for author:
Found 11 papers, 6 papers with code
Learning Stabilizing Policies in Stochastic Control Systems
In this work, we address the problem of learning provably stable neural network policies for stochastic control systems.
Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning
This work revisits the robustness-accuracy trade-off in robot learning by systematically analyzing if recent advances in robust training methods and theory in conjunction with adversarial robot learning can make adversarial training suitable for real-world robot applications.
Stability Verification in Stochastic Control Systems via Neural Network Supermartingales
We consider the problem of formally verifying almost-sure (a. s.) asymptotic stability in discrete-time nonlinear stochastic control systems.
Infinite Time Horizon Safety of Bayesian Neural Networks
Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network's prediction.
GoTube: Scalable Stochastic Verification of Continuous-Depth Models
Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states.
Adversarial Training is Not Ready for Robot Learning
Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop.
Scalable Verification of Quantized Neural Networks (Technical Report)
In this paper, we show that verifying the bit-exact implementation of quantized neural networks with bit-vector specifications is PSPACE-hard, even though verifying idealized real-valued networks and satisfiability of bit-vector specifications alone are each in NP.
Neural circuit policies enabling auditable autonomy
A central goal of artificial intelligence in high-stakes decision-making applications is to design a single algorithm that simultaneously expresses generalizability by learning coherent representations of their world and interpretable explanations of its dynamics.
Into the Unknown: Active Monitoring of Neural Networks
To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network.
Formal Methods with a Touch of Magic
Machine learning and formal methods have complimentary benefits and drawbacks.
Outside the Box: Abstraction-Based Monitoring of Neural Networks
Neural networks have demonstrated unmatched performance in a range of classification tasks.
