Elliot J. Crowley
Papers
2
Total Citations
40
H-Index
2
About
Elliot J. Crowley is a researcher specializing in the optimization and efficient deployment of deep learning systems, with a particular focus on Convolutional Neural Networks (CNNs). His work addresses one of the most pressing challenges in modern artificial intelligence: making computationally intensive neural networks practical for resource-constrained environments such as mobile robots and medical assistance devices. Crowley's most notable contribution, "Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks" (2018), has garnered significant attention within the community, accumulating 40 citations across its publications. This work systematically examines optimization strategies that span the entire computational stack, providing researchers and engineers with a structured framework for reducing the deployment barriers associated with CNNs. By tackling inefficiencies at multiple levels simultaneously, rather than in isolation, Crowley's approach offers a more holistic pathway to making powerful vision-based models accessible on edge devices. His research sits at the intersection of computer architecture, machine learning, and systems engineering — a rare and valuable combination. For students and practitioners interested in embedded AI, neural network compression, or real-world deep learning deployment, Crowley's work represents an essential foundation for understanding how theoretical models can be made practically viable.
Research Focus
Key Achievements
Top Papers
- 1
- 2