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

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

Yannic Kilcher via YouTube Direct link

- Aside: ImageNet V2

7 of 8

7 of 8

- Aside: ImageNet V2

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

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

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Intro & Overview
  2. 2 - Deep Learning at its limits
  3. 3 - The cost of overparameterization
  4. 4 - Extrapolating power usage and CO2 emissions
  5. 5 - We cannot just continue scaling up
  6. 6 - Current solution attempts
  7. 7 - Aside: ImageNet V2
  8. 8 - Are symbolic methods the way out?

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.