AI4Health Lecture Series: Ute Schmid and Bettina Finzel

Beschreibung

The next talk of the AI4Health lecture series will continue on November 04 with a talk on "Learning from Mutual Explanations for Cooperative Decision Making in Medicine" by Ute Schmid and Bettina Finzel (Bamberg University, Germany).

Learning from Mutual Explanations for Cooperative Decision Making in Medicine

Abstract: Medical decision making is one of the most relevant real world domains where intelligent support is necessary to help human experts master the ever growing complexity. At the same time, standard approaches of data driven black box machine learning are not recommendable since medicine is a highly sensitive domain where errors may have fatal consequences. In the talk, we will advocate interactive machine learning from mutual explanations to overcome typical problems of purely data driven approaches to machine learning. Mutual explanations, realised with the help of an interpretable machine learning approach, allow to incorporate expert knowledge in the learning process and support the correction of erroneous labels as well as dealing with noise. Mutual explanations therefore constitute a framework for explainable, comprehensible and correctable classification. Specifically, we present an extension of the inductive logic programming system Aleph which allows for interactive learning. We introduce our application LearnWithME which is based on this extension. LearnWithME gets input from a classifier such as a Convolutional Neural Net‘s prediction on medical images. Medical experts can ask for verbal explanations in order to evaluate the prediction. Through interaction with the verbal statements they can correct classification decisions and in addition can also correct the explanations. Thereby, expert knowledge is taken into account in form of constraints for model adaptation.

- See more at: https://acc.uni.lu/ai4health

We invite you to join this Webinars.

Meeting link:
https://unilu.webex.com/unilu/j.php?MTID=m060774148c89025957b2831d3031c1fc

Meeting number (access code): 163 267 6786
Meeting password: UL-AIForHCWebs

Host key: 478625 

See more at: acc.uni.lu/ai4health