CANCELLED: Deep Learning with Bayesian Principles, Emtiyaz Khan

Machine Learning Tokyo
Machine Learning Tokyo
Public group

Canceled

Location image of event venue

Details

This event is cancelled – postponed. Many companies and public institutions have taken precautions due to the current situation around the corona virus. The MLT leadership team has decided to cancel – postpone events until the situation has improved. Thank you for your understanding. If you have any questions, please get in touch [masked]

____________________________________________________________________________________

We are honored to welcome Mohammad Emtiyaz Khan (RIKEN AIP) for a talk on "Deep Learning with Bayesian Principles" at Mirai Lab Palette in Otemachi. In December he gave a 2-hour tutorial at NeurIPS in Vancouver, that received a lot of fantastic feedback from the machine learning research community and we're excited that he has agreed to give talk and Q&A session for the MLT community in Tokyo.

Recommended prep:
"Deep Learning with Bayesian Principles" at NeurIPS 2019: https://slideslive.com/38923183/deep-learning-with-bayesian-principles
[Paper] https://emtiyaz.github.io/papers/learning_from_bayes.pdf

📌 SCHEDULE

● 18:30 Doors Open
● 19:00 Welcome words
● 19:10 "Deep Learning with Bayesian Principles", Mohammad Emtiyaz Khan
● 20:10 Q&A
● 21:00 Closing

📌 TALK

Deep learning and Bayesian learning are considered two entirely different fields often used in complementary settings. This talk will introduce modern Bayesian principles to bridge the gap between the two fields. I will discuss a new learning rule, called the Bayesian learning rule, and its importance in improving many aspects of deep learning.

📌 SPEAKER

Emtiyaz Khan (also known as Emti) is a team leader at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bayesian Inference Team. He has previously worked at EPFL (Switzerland) and UBC (Canada). The main goal of Emti’s research is to understand the principles of learning from data and use them to develop algorithms that can learn like living beings.

💙 THANK YOU
Huge thank you goes out to Sumitomo Corporation and MIRAI LAB PALETTE for having us at their brand new co-working space in Otemachi. Find more information about the space here: https://www.sumitomocorp.com/ja/jp/palette/place/hub.html

MLT PATRON
Become a MLT Patron and help us to keep MLT meetups like this inclusive and for free. https://www.patreon.com/MLTOKYO

FIND MLT RESOURCES
Github: https://github.com/Machine-Learning-Tokyo
Youtube: https://www.youtube.com/MLTOKYO
Slack: https://goo.gl/WnbYUP

RECRUITING
MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters and consultants looking to hire or sell their services do not come to this event.