kr100 – kr300

Stockholm AI Summit #15 | AI interpretability - talks and panel discussion

Event Information

Share this event

Date and Time

Location

Location

Embassy House

Linnégatan 89C

Stockholm

Sweden

View Map

Refund Policy

Refund Policy

Refunds up to 1 day before event

Event description

Description

We are glad to kick off our event series after the summer with AI Summit #15 around the topic of interpretable AI. There will be two great talks followed by a panel discussion on the topic.

Theme:
Interpretable AI - what is it, why is it relevant and how is it used in practice?


Interpretable AI has been one of the popular topics in the AI-community in the recent years. During this Summit, we will get a nice overview of the current state of the field by our two speakers Amir Hossein Rahnama (researcher at KTH within interpretable AI) and Mikael Huss (data scientist at Peltarion with a PhD from KTH). To round off the evening, there will be a panel discussion titled "Interpretable AI in practice - how, when and why?" with Amir Hossein Rahnama and Mikael Huss, as well as Natallia Lundqvist (Machine Learning Research Engineer at Mathem. PhD from Stockholm University), Sepideh Pashami (Assistant Professor at Halmstad University. Phd from Örebro University), Viktor Qvarfordt (Machine Learning Engineer at Sana Labs) and Stefan Magureanu (Machine Learning Research Engineer at Klarna. PhD from KTH)

For this AI Summit, we will be hosted by Embassy, a co-working space for tech startups.

Please do show up even if you are not able to make it for 17:30 - late arrivals are welcomed.

The schedule (preliminary):

17:30 - 18:00 Registrations, mingle, food and drinks.

18:00 - 18:40 Amir Hossein Rahnama: Troubling trends in Interpretable Machine Learning Research

"In the post-deep learning era, since highly accurate models are now accessible and are running in production, we are faced with a new challenge: Will they perform as accurately on the new data they face out in the wild? Can we supervise them by "interpreting" their predictions? Can we "trust" their prediction? In this talk, I will present you some challenges of defining trust and interpretability in Machine Learning. Besides, I will present important works of research in the domain and how they approach interpretability and leave you with some open question to take home and reflect upon"

18:40 - 18:55 Break

18:55 - 19:35 Mikael Huss: Interpretability in machine learning projects

"The topic of interpretability is broad and hard to get the hang of, partly because different types of interpretability are needed at different stages of a machine learning project’s lifetime. In this talk, I will give an overview of different flavors of interpretability methods and provide a few examples from real-life projects"

19:35 - 19:50 Break

19:50 - 20:35 Panel discussion - Interpretability in practice - how, when, why?

Amir Hossein Rahnama - Researcher on Interpretable AI at KTH.

Mikael Huss - Data Scientist at Peltarion. PhD from KTH.

Natallia Lundqvist - Machine Learning Research Engineer at Mathem. PhD from Stockholm University.

Sepideh Pashami - Assistant Professor at Halmstad University. Phd from Örebro University.

Viktor Qvarfordt - Machine Learning Engineer at Sana Labs.

Stefan Magureanu - Machine Learning Research Engineer at Klarna. PhD from KTH.

20:35 - 21:00 Mingle


Moderator:
Patrik Tran, Chairman Stockholm AI


About Stockholm AI:
Stockholm AI is a non profit organisation serving as an open forum to bring industry professionals and researchers in the Stockholm area together to discuss recent and and future developments. We arrange meetups, hackathons, study groups and other events that cover a wide range of topics from the field of AI, with the aim of making Stockholm a natural centre in the world of machine learning.

For more information, visit our website stockholm.ai

Share with friends

Date and Time

Location

Embassy House

Linnégatan 89C

Stockholm

Sweden

View Map

Refund Policy

Refunds up to 1 day before event

Save This Event

Event Saved