Search Results for author:
Found 5 papers, 2 papers with code
Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)
This in turn allows the analysis of NN safety properties using the new framework, in addition to all the NN properties already included with FANNet.
Poster: Link between Bias, Node Sensitivity and Long-Tail Distribution in trained DNNs
Owing to their remarkable learning (and relearning) capabilities, deep neural networks (DNNs) find use in numerous real-world applications.
UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks
In contrast, UnbiasedNets provides a notable improvement over existing works, while even reducing the robustness bias significantly in some cases, as observed by comparing the NNs trained on the diversified and original datasets.
Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead
Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities.
FANNet: Formal Analysis of Noise Tolerance, Training Bias and Input Sensitivity in Neural Networks
With a constant improvement in the network architectures and training methodologies, Neural Networks (NNs) are increasingly being deployed in real-world Machine Learning systems.
