Towards Green AI by Reducing Training Effort of Recurrent Neural Networks Using Hyper-Parameter Optimization with Dynamic Stopping Criteria

Neural networks have become a leading model in modern machine learning, able to model even the most complex data. For them to be properly trained, however, a lot of computational resources are required. With the carbon footprint of ever-growing adoption of neural networks in mind, an approach to red...

Full description

Saved in:
Bibliographic Details
Main Authors: Podgorelec, Vili, Fister, Iztok, Vrbancic, Grega
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Carbon footprint
Computational modeling
Data models
Green AI
hyper-parameter optimization
machine learning
neural networks
Optimization
Prediction algorithms
Predictive models
Recurrent neural networks
resource optimization
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks have become a leading model in modern machine learning, able to model even the most complex data. For them to be properly trained, however, a lot of computational resources are required. With the carbon footprint of ever-growing adoption of neural networks in mind, an approach to reduce the required training resources would be very welcome. We designed a new training effort reduction method based on the calculation of area under the normalized loss curve and assessed it on the electricity consumption forecasting problem with the recurrent neural networks. The results show that the proposed method was able to considerably reduce the amount of computational resources, while maintaining the predictive performance, and thus contributing towards the Green AI.
ISSN:1949-0488
DOI:10.1109/SISY62279.2024.10737555