The Computational Limits of Deep Learning

07/10/2020
by   Neil C. Thompson, et al.
378

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 recognition, voice recognition, translation, and other tasks. But this progress has come with a voracious appetite for computing power. This article reports on the computational demands of Deep Learning applications in five prominent application areas and shows that progress in all five 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, which will either have to come from changes to deep learning or from moving to other machine learning methods.

READ FULL TEXT

page 9

page 12

research
01/02/2018

Deep Learning: A Critical Appraisal

Although deep learning has historical roots going back decades, neither ...
research
07/16/2022

Deep Learning and Its Applications to WiFi Human Sensing: A Benchmark and A Tutorial

WiFi sensing has been evolving rapidly in recent years. Empowered by pro...
research
04/25/2019

Optimal Approach for Image Recognition using Deep Convolutional Architecture

In the recent time deep learning has achieved huge popularity due to its...
research
07/10/2020

Cloud Detection through Wavelet Transforms in Machine Learning and Deep Learning

Cloud detection is a specialized application of image recognition and ob...
research
08/12/2022

ARCHITECTURAL PARADIGM OF DEEP LEARNING

Deep learning has been trendy and intriguing in recent years in machine ...
research
03/01/2017

Evolving Deep Neural Networks

The success of deep learning depends on finding an architecture to fit t...
research
11/01/2022

Exploring Effects of Computational Parameter Changes to Image Recognition Systems

Image recognition tasks typically use deep learning and require enormous...

Please sign up or login with your details

Forgot password? Click here to reset