Date(s) - 10/06/2019 - 13/06/2019
This year the CHIST-ERA call will bring an interesting topic for our SGAICO community namely Explainable Machine-Learning-based Artificial Intelligence.
If you are interested in this hot topic of AI research you might consider participating the CHIST-ERA Conference in Tallin.
Here some text form the website as a teaser for you:
In the Call 2019, expected to be published in October 2019, two new and hot topics will be addressed, namely Explainable Machine-Learning-based Artificial Intelligence and Novel Computational Approaches for Environmental Sustainability.
The following topic keywords are given as illustration only. The CHIST-ERA Conference 2019 (Tallin, June 11-13) will bring together scientists and CHIST-ERA representatives in order to identify and formulate promising scientific and technological challenges at the frontier of research with a view to refine the scientific content of the call. The conference will be open to the research community.
Topic 1. Explainable Machine Learning-based Artificial Intelligence
Machine learning algorithms, especially deep neural networks, have become very popular in a large variety of applications. These algorithms can learn from examples to generalize classification or regression tasks and successfully apply the learned models to unknown data. Usually, these algorithms transfer input data into abstract representations that are highly effective but difficult to understand for humans, and are considered as ‘black boxes’. Hence, in most cases, neither the algorithms nor the researchers are able to explain how and why a certain prediction has been made. However, for many applications, it is essential that detailed information on the prediction is given to users so that they can understand the decisions that are derived from it. This is important for users to trust the decisions made by the system and to better use them. The objective of research on this topic is to make machine learning algorithms explainable, thereby reducing vulnerability and adding transparency by giving users detailed information why systems have arrived at a particular decision.
Application sectors: All application sectors of machine learning such as healthcare, bioinformatics, multimedia, linguistics, human computer interaction, machine translation, autonomous vehicles, etc.
Keywords: Artificial intelligence; machine learning; deep learning; explainability; transparency; accountability
Copyright © 2017 | Swiss Group for Artificial Intelligence and Cognitive Science