You are about to action:

Object being modified by the action

Do you want to proceed?

Share Video Link

https://www.bitchute.com/video/v5v26DeTywcn/

Click to copy, then share by pasting into your messages, comments, social media posts and websites.

Embed Video HTML

Click to copy, then add into your webpages so users can view and engage with this video from your site.

Share to Social Media

Share to social media by clicking on the quick share links.

Report Content

Reason

Please select the most appropriate reason from the list provided.

Note: For a more detailed description of each reason, see our Community Guidelines.

Additional Comments

Please add any additonal comments that will help with the assessment of your request.

Note: Copyright claims must contain all the items specified within the Copyright Policy.

Email Submissions

We also accept reports via email. Please see the Guidelines Enforcement Process for instructions on how to make a request via email.

Thank you for submitting your report

We will investigate and take the appropriate action.

Add to Playlist

[Live Machine Learning Research] Plain Self-Ensembles (I actually DISCOVER SOMETHING) - Part 1

Next video playing soon

Click to cancel

Autoplay has been paused

Click to watch next video

First published at 14:49 UTC on July 6th, 2020.

Yannic Kilcher

subscribers

Your platform for uncensored ideas. BitChute Premium.

BitChute Advertisement

I share my progress of implementing a research idea from scratch. I attempt to build an ensemble model out of students of label-free self-distillation without any additional data or augmentation. Turns out, it actually works, and interestingly, the more students I employ, the better the accuracy. This leads to the hypothesis that the ensemble effect is not a process of extracting more information from labels.

OUTLINE:
0:00 - Introduction
2:10 - Research Idea
4:15 - Adjusting the Codebase
25:00 - Teacher and Student Models
52:30 - Shipping to the Server
1:03:40 - Results
1:14:50 - Conclusion

Code: https://github.com/yk/PyTorch_CIFAR10

References:
My Video on SimCLRv2: https://youtu.be/2lkUNDZld-4
Born-Again Neural Networks: https://arxiv.org/abs/1805.04770
Deep Ensembles: A Loss Landscape Perspective: https://arxiv.org/abs/1912.02757

Links:
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://discord.gg/4H8xxDF
BitChute: https://www.bitchute.com/channel/yannic-kilcher
Minds: https://www.minds.com/ykilcher
Parler: https://parler.com/profile/YannicKilcher

LESS