MLSS 2021
Machine Learning Summer School 2021
MLSS 2021 TAIPEI (Machine Learning Summer School)
MLSS(http://mlss.cc)為一國際機器學習暑期課程組織，始於2002 年，主要目的為推廣統計機器學習和推論的最新技術及方法。本組織每年皆有各國家申請辦理活動，邀請的講師為國際各相關領域的專家教授，提供的主題涵蓋基礎知識，到最新機器學習的實踐。主辦單位希望藉此活動，鼓勵臺灣優秀AI 研究人才與國際社群交流，並形塑臺灣成為亞洲AI 領域區域人才中心。藉由MLSS 的多年累積之領域資源之連結，邀請各國知名領域專家授課指導，徵集世界各國優秀學生參與。
MLSS 2021 TAIPEI請見 https://ai.ntu.edu.tw/mlss2021/
▍Speaker: Csaba Szepesvari
Title: Large scale learning and planning in reinforcement learning
▍Speaker: Hsuan-Tien Lin
Title: Cost-sensitive Classification: Techniques and Stories
▍Speaker: Jason Lee
Title: Theory of deep learning
▍Industrial Talk: Appier Inc.
▍Speaker: Shou-De Lin
Title: Machine Learning as a Services: Challenges and Opportunities
▍Speaker: Henry Kautz
Title: Neuro-symbolic systems and the history of AI
▍Speaker: Chun-Yi Lee
Title: Fundamentals and Applications of Deep Reinforcement Learning
▍Industrial Talk: Perfect Corp.
▍Speaker: Johnny Tseng
Title: Transform the Beauty Industry through AI + AR: Perfect Corp’s Innovative Vision into the Digital Era
▍Speaker: Marco Cuturi
▍Title: Optimal transport
▍Speaker: Kai-Wei Chang
Title: Bias and Fairness in NLP
▍Industrial Talk: CyberLink Corp.
▍Speaker: David Lee
Title: Developing a World-Class AI Facial Recognition Solution – CyberLink FaceMe®
▍Speaker: Cho-Jui Hsieh
Title: Neural Architecture Search and AutoML
▍Speaker: Pin-Yu Chen
Title: Holistic Adversarial Robustness for Deep Learning
▍Speaker: John Shawe-Taylor
Title: An introduction to Statistical Learning Theory and PAC-Bayes Analysis
▍Speaker: Hung-Yi Lee
Title: Deep Learning for Speech Processing
▍Speaker: Philipp Krähenbühl
Title: Computer Vision
▍Speaker: Song Han
Title: TinyML and Efficient Deep Learning
▍Speakers: Thang Vu, Shang-Wen Li
Title: Meta Learning for Human Language Processing
▍Speaker: Been Kim
Title: Interpretable machine learning
▍Speaker: Karteek Alahari
Title: Continual Visual Learning
▍Speaker: Michael Bronstein
Title: Geometric Deep Learning
▍Speaker: Shou-De Lin
Title: Machine Learning in Practice – what to do if my ML models fail to achieve a desirable quality ?
▍Panel Discussion
Panelists:
* Cho-Jui Hsieh
* Pin-Yu Chen
* Soheil Feizi
* Sijia Liu
Title: Trustworthy Machine Learning: Challenges and Opportunities
▍Panel Discussion
Panelists:
* Shinji Watanabe
* Shang-Wen Li
* Mirco Ravanelli
* Titouan Parcollet
Title:Self-supervised Learning and Universal Modeling for Speech and Audio Processing – Benchmarking and Open-source Toolkits
▍Speaker: Arthur Gretton
Title: Probability Divergences and Generative Models
