80 citations · 622 across the 22 of their papers we have counts for
23 papers
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
Mark D. McDonnell, Dong Gong, Ehsan Abbasnejad +1
Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task…
RanPAC: Random Projections and Pre-trained Models for Continual Learning
Mark D. McDonnell, Dong Gong, Amin Parveneh +2
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tac…
Planet Four: A Neural Network's Search For Polar Spring-time Fans On Mars
Mark D. McDonnell, Eriita Jones, Megan E. Schwamb +3
Dark deposits visible from orbit appear in the Martian south polar region during the springtime. These are thought to form from explosive jets of carbon dioxide gas breaking throug…
Single-bit-per-weight deep convolutional neural networks without batch-normalization layers for embedded systems
Mark D. McDonnell, Hesham Mostafa, Runchun Wang +1
Batch-normalization (BN) layers are thought to be an integrally important layer type in today's state-of-the-art deep convolutional neural networks for computer vision tasks such a…
Diagnosing Convolutional Neural Networks using their Spectral Response
Victor Stamatescu, Mark D. McDonnell
Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to…
Training wide residual networks for deployment using a single bit for each weight
Mark D. McDonnell
For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and…