YoVDO

How Far Can We Scale Up? Deep Learning's Diminishing Returns

Offered By: Yannic Kilcher via YouTube

Tags

Deep Learning Courses CO2 Emissions Courses

Course Description

Overview

Explore the limits of exponential scaling in AI and potential solutions in this 20-minute video review of an article on deep learning's diminishing returns. Examine the impressive results achieved through massive increases in computational power and data, while considering the challenges of overparameterization, power usage, and CO2 emissions. Delve into current attempts to address scaling issues, including a discussion on ImageNet V2 and the potential of symbolic methods. Gain insights into the future of AI development and the need for more efficient approaches to continue advancing the field.

Syllabus

- Intro & Overview
- Deep Learning at its limits
- The cost of overparameterization
- Extrapolating power usage and CO2 emissions
- We cannot just continue scaling up
- Current solution attempts
- Aside: ImageNet V2
- Are symbolic methods the way out?


Taught by

Yannic Kilcher

Related Courses

Neural Networks for Machine Learning
University of Toronto via Coursera
機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera
Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera
Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera
Leading Ambitious Teaching and Learning
Microsoft via edX