MLT __init__ Session #15: Deep Learning on a Data Diet

📌 Paper Reading & Discussion 📌 Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite: Deep Learning on a Data Diet: Finding Important Examples Early in Training arxiv.org/abs/2107.07075 📌 Presenter: Gintare Karolina Dziugaite 👉 PRESENTER BIO Karolina is a senior research scientist at Google Brain, based in Toronto, an adjunct professor in the McGill University School of Computer Science, and an associate industry member of Mila, the Quebec AI Institute. Her research combines theoretical and empirical approaches to understanding deep learning, with a focus on generalization and network compression. Karolina obtained her Ph.D. in machine learning from the University of Cambridge, under the supervision of Zoubin Ghahramani. Before that, she studied Mathematics at the University of Warwick and read Part III in Mathematics at the University of Cambridge, receiving a Masters of Advanced Study (MASt) in Applied Mathematics. Personal website: gkdz.org 🤖 ABOUT MLT _init_ 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 github.com/Machine-Learning-Tokyo/__init__ ● ORGANIZERS’ BIO 👉 J. Miguel Valverde is a Ph.D. student at the University of Eastern Finland working on Rodent MRI Segmentation with Deep Learning. He has multiple research experiences across Europe and Japan. In his free time, he enjoys nature, learning languages, programming, and making food. twitter.com/jmlipman 👉 Jayson Cunanan is an AI Researcher/Engineer at AI inside. He obtained a Ph.D. in Mathematics at Nagoya University and was awarded the JSPS Postdoctoral Fellowship 2018. In his free time, he loves playing the guitar. www.linkedin.com/in/jayson-cunanan-phd/ twitter.com/jsonmathsAi ========================= MLT (Machine Learning Tokyo) site: machinelearningtokyo.com/ github: github.com/Machine-Learning-Tokyo slack: machinelearningtokyo.slack.com/messages discuss: discuss.mltokyo.ai/ twitter: twitter.com/__MLT__ meetup: www.meetup.com/Machine-Learning-Tokyo/ facebook: www.facebook.com/machinelearningtokyo

• #science_technology
• #mlt
• #ai
• #machine_learning
• #deep_learning
• #machine_learning_tokyo