Angus Galloway

Bounding generalization error with input compression: An empirical study with infinite-width networks

Jul 19, 2022
Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, Graham W. Taylor

Figure 2 for Bounding generalization error with input compression: An empirical study with infinite-width networks

Figure 3 for Bounding generalization error with input compression: An empirical study with infinite-width networks

Figure 4 for Bounding generalization error with input compression: An empirical study with infinite-width networks

* 12 pages main content, 26 pages total

Access Paper or Ask Questions

Monitoring Shortcut Learning using Mutual Information

Jun 27, 2022
Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor

Figure 2 for Monitoring Shortcut Learning using Mutual Information

Figure 3 for Monitoring Shortcut Learning using Mutual Information

Figure 4 for Monitoring Shortcut Learning using Mutual Information

* Accepted at ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability

Access Paper or Ask Questions

Batch Normalization is a Cause of Adversarial Vulnerability

May 29, 2019
Angus Galloway, Anna Golubeva, Thomas Tanay, Medhat Moussa, Graham W. Taylor

Figure 2 for Batch Normalization is a Cause of Adversarial Vulnerability

Figure 3 for Batch Normalization is a Cause of Adversarial Vulnerability

Figure 4 for Batch Normalization is a Cause of Adversarial Vulnerability

* To appear in the ICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena

Access Paper or Ask Questions

Adversarial Examples as an Input-Fault Tolerance Problem

Nov 30, 2018
Angus Galloway, Anna Golubeva, Graham W. Taylor

Figure 2 for Adversarial Examples as an Input-Fault Tolerance Problem

Figure 3 for Adversarial Examples as an Input-Fault Tolerance Problem

Figure 4 for Adversarial Examples as an Input-Fault Tolerance Problem

* NIPS 2018 Workshop on Security and Machine Learning. Source available at https://github.com/uoguelph-mlrg/nips18-secml-advex-input-fault

Access Paper or Ask Questions

Adversarial Training Versus Weight Decay

Jul 23, 2018
Angus Galloway, Thomas Tanay, Graham W. Taylor

Figure 2 for Adversarial Training Versus Weight Decay

Figure 3 for Adversarial Training Versus Weight Decay

Figure 4 for Adversarial Training Versus Weight Decay

Access Paper or Ask Questions

Predicting Adversarial Examples with High Confidence

Feb 13, 2018
Angus Galloway, Graham W. Taylor, Medhat Moussa

Figure 2 for Predicting Adversarial Examples with High Confidence

Figure 3 for Predicting Adversarial Examples with High Confidence

Figure 4 for Predicting Adversarial Examples with High Confidence

* Under review by the International Conference on Machine Learning (ICML)

Access Paper or Ask Questions

Attacking Binarized Neural Networks

Jan 31, 2018
Angus Galloway, Graham W. Taylor, Medhat Moussa

Figure 2 for Attacking Binarized Neural Networks

Figure 3 for Attacking Binarized Neural Networks

Figure 4 for Attacking Binarized Neural Networks

* Published as a conference paper at ICLR 2018

Access Paper or Ask Questions

The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment

Feb 18, 2017
Angus Galloway, Graham W. Taylor, Aaron Ramsay, Medhat Moussa

Figure 2 for The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment

Figure 3 for The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment

Figure 4 for The Ciona17 Dataset for Semantic Segmentation of Invasive Species in a Marine Aquaculture Environment

* Submitted to the Conference on Computer and Robot Vision (CRV) 2017

Access Paper or Ask Questions