Search Results for author:
Found 4 papers, 0 papers with code
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 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.
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.
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.
