ICML 2019 Expo Workshop
July 12, 2020
Recent Work on Machine Learning at NAVER
Sponsor: NAVER | LINE
Julien Perez (NAVER LABS Europe), Irene Maxwell (NAVER LABS Europe)
Julien Perez (NAVER LABS Europe), Christopher Dance (NAVER LABS Europe), Quentin Grail (NAVER LABS Europe), JiHoon Kim (NAVER), Dongyoon Wee (NAVER), Sanghyuk Chun (NAVER)
Advances in deep learning have recently fuelled unprecedented progress across a number of disciplines and, in particular, those of computer vision and natural language. An associated outcome has been the dramatic improvement in the challenging task of ‘machine comprehension’ which depends on both common-sense acquisition and reasoning models. The impact that deep learning has had on these two fundamental problems has likewise enabled progress in applications in machine reading, visual question answering, and imagination-based control. In this half-day workshop, NAVER LABS and Clova AI will demonstrate how these research topics are actively being pursued at an industrial scale. Clova AI is the AI content and service platform of NAVER, South Korea’s internet giant which runs the world’s 5th largest search engine (28 M unique visitors per day) and offers over 130 content services. NAVER is ranked in the Top 10 most innovative global companies (Forbes 2018) and is 6th on Fortune’s ‘Future 50’ list (2018).
Schedule: 14:00 - 14:30 Introduction, Julien PEREZ, NAVER LABS Europe & Ji-Hoon KIM, NAVER/CLOVA AI Research 14:30 – 15.20 Machine reading & comprehension, Quentin Grail, NAVER LABS Europe 15:20 – 16:00 An introduction to Practical AutoML used in Clova AI, JiHoon Kim, NAVER/ CLOVA AI Research 16:00 – 16:30 Break 16:30 – 17:30 Optimal Policies for Observing Time Series and Related Restless Bandits, Christopher Dance, NAVER LABS Europe 17:30 – 18:00 Spatio-temporal modeling for pose tracking and action recognition, Dongyoon Wee, Video Tech Leader, NAVER/LINE 18:00 - 18:30 An empirical evaluation on the generalization ability of regularization methods, Sanghyuk Chun, NAVER/ CLOVA AI Research