Trustworthy AI: Bayesian deep learning | AI FOR GOOD DISCOVERY

Channel:

AI for Good

Subscribers:

19,700

Published on June 10, 2021 12:00:00 AM ● Video Link: https://www.youtube.com/watch?v=lIo1O08YK2c

Duration: 0:00

453 views

0

Bayesian models are rooted in Bayesian statistics and easily benefit from the vast literature in the field. In contrast, deep learning lacks a solid mathematical grounding. Instead, empirical developments in deep learning are often justified by metaphors, evading the unexplained principles at play. These two fields are perceived as fairly antipodal to each other in their respective communities. It is perhaps astonishing then that most modern deep learning models can be cast as performing approximate inference in a Bayesian setting. The implications of this are profound: we can use the rich Bayesian statistics literature with deep learning models, explain away many of the curiosities with ad hoc techniques, combine results from deep learning into Bayesian modelling, and much more. In this talk, Yarin Gal will discuss interesting advances in the field.

🔴 Watch the latest #AIforGood videos:


Explore more #AIforGood content:
1️ ⃣    • Top Hits  
2️ ⃣    • AI for Good Webinars  
3️ ⃣    • AI for Good Keynotes  

📅 Discover what's next on our programmhttps://aiforgood.itu.int/programme/me/

Social Media:
Websithttps://aiforgood.itu.int/nt/
Twittehttps://twitter.com/ITU_AIForGoodd  
LinkedIn Paghttps://www.linkedin.com/company/265119077  
LinkedIn Grouhttps://www.linkedin.com/groups/85677488  
Instagrahttps://www.instagram.com/aiforgoodd  
Faceboohttps://www.facebook.com/AIforGoodd  

WHAT IS TRUSTWORTHY AI SERIES?
Artificial Intelligence (AI) systems have steadily grown in complexity, gaining predictivity often at the expense of interpretability, robustness and trustworthiness. Deep neural networks are a prime example of this development. While reaching “superhuman” performances in various complex tasks, these models are susceptible to errors when confronted with tiny (adversarial) variations of the input – variations which are either not noticeable or can be handled reliably by humans. This expert talk series will discuss these challenges of current AI technology and will present new research aiming at overcoming these limitations and developing AI systems which can be certified to be trustworthy and robust.

What is AI for Good?
The AI for Good series is the leading action-oriented, global & inclusive United Nations platform on AI. The Summit is organized all year, always online, in Geneva by the ITU with XPRIZE Foundation in partnership with over 35 sister United Nations agencies, Switzerland and ACM. The goal is to identify practical applications of AI and scale those solutions for global impact.

Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.

#trustworthyAI #robustAI