Optimizing AI for Sustainability
21 attendees from 8 groups hosting
Hosted by Data Science Madison
Details
The session outlines a three-pillar approach to sustainable AI:
Energy & Infrastructure: Leveraging cloud computing's superior energy efficiency compared to on-premises solutions and selecting regions with renewable energy sources.
Model Optimization: Choosing appropriately-sized models for specific tasks and implementing techniques like model distillation, quantization, pruning, and prompt caching to reduce resource consumption while maintaining performance.
Frugality: Questioning whether AI is necessary for specific problems and considering less resource-intensive alternatives.
The presentation emphasizes incorporating sustainability as a core requirement alongside cost and security considerations in AI development.
AI summary
By Meetup
Session for AI practitioners on sustainable AI, detailing pillars and how to reduce energy use by choosing right-sized models and applying pruning/quantization.
AI summary
By Meetup
Session for AI practitioners on sustainable AI, detailing pillars and how to reduce energy use by choosing right-sized models and applying pruning/quantization.
