A Transition System Abstraction Framework for Neural Network Dynamical System Models

arXiv:2402.11739v1 Announce Type: cross
Abstract: 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. To begin with, the localized working zone will be segmented into multiple localized partitions under the data-driven Maximum Entropy (ME) partitioning method. Then, the transition matrix will be obtained based on the set-valued reachability analysis of neural networks. Finally, applications to human handwriting …

abstract abstraction applications arxiv behavior cs.lg cs.sy eess.sy framework human interpretability model interpretability multiple network neural network paper systems transition type verification will