Search Results for author:
Found 16 papers, 5 papers with code
A Transition System Abstraction Framework for Neural Network Dynamical System Models
This paper proposes a transition system abstraction framework for neural network dynamical system models to enhance the model interpretability, with applications to complex dynamical systems such as human behavior learning and verification.
Compression Repair for Feedforward Neural Networks Based on Model Equivalence Evaluation
Based on the computed output discrepancy, the repairing method first initializes a new training set for the compressed networks to narrow down the discrepancy between the two neural networks and improve the performance of the compressed network.
A Data-Driven Hybrid Automaton Framework to Modeling Complex Dynamical Systems
Then, a collection of small-scale neural networks that are computationally efficient are trained as the local dynamical description for their corresponding topologies.
Guaranteed Quantization Error Computation for Neural Network Model Compression
Neural network model compression techniques can address the computation issue of deep neural networks on embedded devices in industrial systems.
Safety Verification of Neural Network Control Systems Using Guaranteed Neural Network Model Reduction
A reachability-based algorithm is proposed to accurately compute the model reduction precision.
Approximate Bisimulation Relations for Neural Networks and Application to Assured Neural Network Compression
In this paper, we propose a concept of approximate bisimulation relation for feedforward neural networks.
Robust Optimization Framework for Training Shallow Neural Networks Using Reachability Method
In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks.
Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach
Then, in combination with reachability methods developed for various dynamical system classes modeled by ordinary differential equations, a recursive algorithm is developed for over-approximating the reachable set of the closed-loop system.
Verification of Deep Convolutional Neural Networks Using ImageStars
Set-based analysis methods can detect or prove the absence of bounded adversarial attacks, which can then be used to evaluate the effectiveness of neural network training methodology.
NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions, such as ReLUs.
Reachability Analysis for Feed-Forward Neural Networks using Face Lattices
To address this challenge, we propose a parallelizable technique to compute exact reachable sets of a neural network to an input set.
Specification-Guided Safety Verification for Feedforward Neural Networks
As such feedforward networks are memoryless, they can be abstractly represented as mathematical functions, and the reachability analysis of the neural network amounts to interval analysis problems.
Verification for Machine Learning, Autonomy, and Neural Networks Survey
This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof.
Reachability Analysis and Safety Verification for Neural Network Control Systems
This paper develops methods for estimating the reachable set and verifying safety properties of dynamical systems under control of neural network-based controllers that may be implemented in embedded software.
Systems and Control
Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations
Due to the complicate, nonlinear, non-convex nature of neural networks, formal safety guarantees for the output behaviors of neural networks will be crucial for their applications in safety-critical systems. In this paper, the output reachable set computation and safety verification problems for a class of neural networks consisting of Rectified Linear Unit (ReLU) activation functions are addressed.
Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks
In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed.
