MLT __init__ Session #9: Self-Distillation as Instance-Specific Label Smoothing
📌 Session #9: Self-Distillation as Instance-Specific Label Smoothing
📌 Paper Reading
📌 Zhang and Sabuncu (2020): Self-distillation as instance-specific label smoothing https://arxiv.org/abs/2006.05065
● WE HIGHLY RECOMMEND READING “DISTILLING THE KNOWLEDGE IN A NEURAL NETWORK” (Hinton et al 2014) AS WELL https://arxiv.org/abs/1503.02531
MLT _init_ is a monthly event led by Jayson Cunanan and J. Miguel Valverde where a paper is first presented by a volunteer and then discussed among all attendees. Our goal is to give participants good initializations to study Deep Learning effectively. We also hope to promote collaboration between participants. We will try to achieve this by:
Discussing fundamental papers whose key ideas apply to state-of-the-art models.
Providing the audience with summaries, codes, and visualizations to help understand the critical parts of a research paper.
Find more information, the videos, and materials from previous sessions in https://github.com/Machine-Learning-T...
📌 Presenter: Mauricio Orbes, Research scientist.
Mauricio Orbes is a research scientist at Omhu (Copenhagen, Denmark) and a Ph.D. candidate at King's College London, School of Biomedical Engineering and Imaging Sciences. My research interest is machine learning in general with a special focus on solving robustness-related issues on deep learning models for real-world complex scenarios, specifically in the field of medical imaging. More info: / mauricio-orbes-b13916157
=========================
MLT (Machine Learning Tokyo)
site:
github: https://github.com/Machine-Learning-T...
slack: https://machinelearningtokyo.slack.co...
discuss: https://discuss.mltokyo.ai/
twitter: / __mlt__
meetup: https://www.meetup.com/Machine-Learni...
facebook: / machinelearningtokyo