The Computational Limits os Deep Learning(Paper-Service)
Group: 02
Course code: FGA0208-T01
Team
Matrícula | Aluno |
---|---|
16/0121019 | Gabriel Filipe Manso Araujo |
16/0122996 | Guilherme Antonio Deusdará Banci |
16/0132550 | Lorrany Azevedo |
15/0018673 | Mikhaelle de Carvalho Bueno |
13/0060941 | Vitor Meireles Oliveira |
13/0138304 | Ygor Torres Galeno |
About
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. Recently, researchers from MIT, UnB, IBM, and Yonsei University published a paper named "The Computational Limits of Learning" and warned society about this issue. 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.
Our project aims to develop a web application for this paper where will be possible for people/community to have access to the data and the paper's analysis, and also allowing them to continuously contribute with it.
Paper link: https://arxiv.org/abs/2007.05558
Screenshots
Add 3 or more screenshots of the project in terms of interface and operation.
Installation
Languages: Javascript
Technologies: NodeJS with Typescript
Describe the prerequisites for running your project and the necessary commands.
Insert a manual or script to further assist.
Usage
Explain how to use your project if there are any steps after the execution command.
Video
Add 1 or more videos with the execution of the final project.
Others
Any other information about your project can be described below.
Running
To make changes on this documentation, just execute the following commands:
git clone https://github.com/UnBArqDsw/2020.1_G2_TCLDL.git
cd 2020.1_G2_TCLDL
cd documentation
docker build -t imagename .
docker run -it -p 8080:8080 imagename