no code implementations • 19 Jul 2022 • Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani Ioannou, Graham W. Taylor
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data.
no code implementations • 27 Jun 2022 • Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, Graham W. Taylor
The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critical domains such as healthcare, finance and autonomous vehicles.
no code implementations • 6 May 2019 • Angus Galloway, Anna Golubeva, Thomas Tanay, Medhat Moussa, Graham W. Taylor
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks.
1 code implementation • 30 Nov 2018 • Angus Galloway, Anna Golubeva, Graham W. Taylor
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input.
no code implementations • 27 Sep 2018 • Angus Galloway, Anna Golubeva, Graham W. Taylor
The generalization ability of deep neural networks (DNNs) is intertwined with model complexity, robustness, and capacity.
2 code implementations • 10 Apr 2018 • Angus Galloway, Thomas Tanay, Graham W. Taylor
Performance-critical machine learning models should be robust to input perturbations not seen during training.
no code implementations • 13 Feb 2018 • Angus Galloway, Graham W. Taylor, Medhat Moussa
It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence.
1 code implementation • ICLR 2018 • Angus Galloway, Graham W. Taylor, Medhat Moussa
Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents.
no code implementations • 18 Feb 2017 • Angus Galloway, Graham W. Taylor, Aaron Ramsay, Medhat Moussa
An original dataset for semantic segmentation, Ciona17, is introduced, which to the best of the authors' knowledge, is the first dataset of its kind with pixel-level annotations pertaining to invasive species in a marine environment.