no code implementations • 9 Oct 2023 • Samet Bayram, Kenneth Barner
GReAT deploys the graph structure of the data into the adversarial training process, resulting in more robust models that better generalize its testing performance and defend against adversarial attacks.
no code implementations • 30 Aug 2022 • Samet Bayram, Kenneth Barner
models are one of the major concerns with an increasing number of effective adversarial attack methods.
1 code implementation • 18 Jun 2021 • Xinjie Lan, Kenneth Barner
However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, which in turn weakens the information theoretic explanation for generalization.
no code implementations • NeurIPS 2021 • Xinjie Lan, Kenneth Barner
The Information Bottleneck (IB) principle has recently attracted great attention to explaining Deep Neural Networks (DNNs), and the key is to accurately estimate the mutual information between a hidden layer and dataset.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Xin Guo, Yu Tian, Qinghan Xue, Panos Lampropoulos, Steven Eliuk, Kenneth Barner, Xiaolong Wang
Catastrophic forgetting in neural networks indicates the performance decreasing of deep learning models on previous tasks while learning new tasks.
no code implementations • 2 Oct 2019 • Bin Zhu, Xin Guo, Kenneth Barner, Charles Boncelet
The task is to predict the cohesive level for a group of people in images.
no code implementations • CVPR 2014 • Yin Zhou, Hang Chang, Kenneth Barner, Paul Spellman, Bahram Parvin
Image-based classification of histology sections plays an important role in predicting clinical outcomes.