Introduction to AI Interpretability

Starts on 05/27/2021

Ends on 06/15/2021

Lecturer

Prof. Henning Müller henning.mueller@hevs.ch, M.Phil. Mara Graziani mara.graziani@hevs.ch and Prof. Jenny Benois-Pineau jenny.benois-pineau@u-bordeaux.fr

Organizers

HES-SO Valais Sw, Univ. Geneva, Univ. Bordeaux

Description

The University of Applied Sciences of Western Switzerland and University of Bordeaux are happy to present this lecture series as a preview of a longer course that may start in Autumn 2021. This course will cover topics such as the definition of AI interpretability, saliency and attention models and the explainability of deep models by feature attribution methods and concept-based attribution with Concept Activation Vectors and Regression Concept Vectors.

Course type

Lecture Series

Schedule

on May 27,  duration 5 courses scheduled as in the following

  • May 27th 16:00 to 17:30 (CEST): Course Lecture 1 [Prof. Henning Müller and Mara Graziani (PhD student)] :  The Where and Why of Interpretability
  • June 10th – Recorded video : Course Lecture 2 [Mara Graziani (PhD student)] :  The three dimensions of interpretability. Activation Maximization and Feature Attribution
  • June 11th 17:00 to 19:00 (CEST): Course Lecture 3 [Prof. Jenny Benois-Pineau] :  From attention models and saliency maps to the explainability of Deep Neural Networks.
  • June 14th  – Recorded video : Course Lecture 4 [Mara Graziani (PhD student)] :  Concept-based interpretability
  • June 15th 16:00 to 17:30 : Course Lecture 5 [Mara Graziani (PhD student)] :  Evaluating your interpretability experiments
    + open Q&A

Other short courses

2021. 06. 17 Go

Deep Learning School

2021. 06. 17 Go

Memory Network

2021. 06. 2 Go

Machine Listening

2021. 06. 2 Go

Deep Learning 2

2021. 06. 2 Go

Image Processing

2021. 06. 1 Go

Machine listening

Cookie Settings

A AIDA - AI Doctoral Academy may use cookies to remember your login data, collect statistics to optimize the functionality of the site and to perform marketing actions based on your interests.


These cookies are necessary to allow the main functionality of the website and are automatically activated when you use this website.
These cookies allow us to analyze the use of the website, so that we can measure and improve its performance.
Allow you to stay in touch with your social network, share content, send and post comments.

Required Cookies They allow you to personalize the commercial offers that are presented to you, directing them to your interests. They can be own or third party cookies. We warn you that, even if you do not accept these cookies, you will receive commercial offers, but without meeting your preferences.

Functional Cookies They offer a more personalized and complete experience, allow you to save preferences, show you content relevant to your taste and send you the alerts you have requested.

Advertising Cookies Allow you to stay in touch with your social network, share content, send and post comments.