The Computational Limits of Deep Learning
Moscow Institute of Thermal Technology · IBM (United States) · +2 more institutions
Abstract
Deep learning's recent history has been one of achievement: from triumphing over humans in the game of Go to world-leading performance in image classification, voice recognition, translation, and other tasks.But this progress has come with a voracious appetite for computing power.This article catalogs the extent of this dependency, showing that progress across a wide variety of applications is strongly reliant on increases in computing power.Extrapolating forward this reliance reveals that progress along current lines is rapidly becoming economically, technically, and environmentally unsustainable.Thus, continued progress in these applications will require dramatically more computationally-efficient methods,…
Citation impact
- FWCI
- 16.11
- Percentile
- 100%
- References
- 161
Authors
4Topics & keywords
- Computer science
- Deep learning
- Artificial intelligence