Operating critical machine learning models in resource constrained regimes
Preprint
Abstract
The accelerated development of machine learning methods, primarily deep learning, are causal to the recent breakthroughs in medical image analysis and computer aided intervention. The resource consumption of deep learning models in terms of amount of training data, compute and energy costs are known to be massive. These large resource costs can be barriers in deploying these models in clinics, globally. To address this, there are cogent efforts within the machine learning community to introduce notions of resource efficiency. For instance, using quantisation to alleviate memory consumption. While most of these methods are shown to reduce the resource utilisation, they could come at a cost in performance. In this work, we probe into the trade-off between resource consumption and performance, specifically, when dealing with models that are used in critical settings such as in clinics.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Addressing fairness in artificial intelligence for medical imagingNature Communications, 2022
- Compute Trends Across Three Eras of Machine Learning2022
- Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and ChallengesIEEE Signal Processing Magazine, 2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- Multi-objective Optimisation Using Evolutionary Algorithms: An Introduction2011
- Problems and solutions in calculating quality-adjusted life years (QALYs)Health and Quality of Life Outcomes, 2003
- BI-RADS Categorization As a Predictor of MalignancyRadiology, 1999
- Continual Learning in Medical Devices: FDA’s Action Plan and Beyond