5 papers
Efficient Neural Hybrid System Learning and Transition System Abstraction for Dynamical Systems
Yejiang Yang, Zihao Mo, Weiming Xiang
This paper proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient way of dynamics learning and system iden…
A Transition System Abstraction Framework for Neural Network Dynamical System Models
Yejiang Yang, Zihao Mo, Hoang-Dung Tran +1
This paper proposes a transition system abstraction framework for neural network dynamical system models to enhance the model interpretability, with applications to complex dynamic…
Compression Repair for Feedforward Neural Networks Based on Model Equivalence Evaluation
Zihao Mo, Yejiang Yang, Shuaizheng Lu +1
In this paper, we propose a method of repairing compressed Feedforward Neural Networks (FNNs) based on equivalence evaluation of two neural networks. In the repairing framework, a…
A Data-Driven Hybrid Automaton Framework to Modeling Complex Dynamical Systems
Yejiang Yang, Zihao Mo, Weiming Xiang
In this paper, a computationally efficient data-driven hybrid automaton model is proposed to capture unknown complex dynamical system behaviors using multiple neural networks. The…
Robust Optimization Framework for Training Shallow Neural Networks Using Reachability Method
Yejiang Yang, Weiming Xiang
In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data…