Jianglin Lan

Filter-based Online Neuro-Fuzzy Model Learning using Noisy Measurements

2023

Neuro-Fuzzy (NF) model is capable of learning the nonlinear mapping between inputs and outputs accurately from training data and is thus a powerful tool for identification of nonlinear dynamic systems. However, when deploying the trained …

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation

2023 · arXiv (Cornell University)

Counterfactual Explanations (CEs) have received increasing interest as a major methodology for explaining neural network classifiers. Usually, CEs for an input-output pair are defined as data points with minimum distance to the input that are …