The scientific work "Explaining the Predictions of Unsupervised Learning Models", developed with the support of the iToBoS project, has been published.
It is part of the Lecture Notes in Computer Science book series (LNAI,volume 13200).
Unsupervised learning is a subfield of machine learning that focuses on learning the structure of data without making use of labels. This implies a different set of learning algorithms than those used for supervised learning, and consequently, also prevents a direct transposition of Explainable AI (XAI) methods from the supervised to the less studied unsupervised setting. In this chapter, we review our recently proposed ‘neuralization-propagation’ (NEON) approach for bringing XAI to workhorses of unsupervised learning such as kernel density estimation and k-means clustering. NEON first converts (without retraining) the unsupervised model into a functionally equivalent neural network so that, in a second step, supervised XAI techniques such as layer-wise relevance propagation (LRP) can be used. The approach is showcased on two application examples: (1) analysis of spending behavior in wholesale customer data and (2) analysis of visual features in industrial and scene images.
Acknowledgements
This work was supported by the German Ministry for Education and Research under Grant 01IS14013A-E, Grant 01GQ1115, Grant 01GQ0850, as BIFOLD (ref. 01IS18025A and ref. 01IS18037A) and Patho234 (ref. 031LO207), the European Union’s Horizon 2020 programme (grant no. 965221), and the German Research Foundation (DFG) as Math+: Berlin Mathematics Research Center (EXC 2046/1, project-ID: 390685689). This work was supported in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grants funded by the Korea Government under Grant 2017-0-00451 (Development of BCI Based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning) and Grant 2019-0-00079 (Artificial Intelligence Graduate School Program, Korea University).
Authors and Affiliations
- ML Group, Department of Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, Germany. Grégoire Montavon, Jacob Kauffmann & Klaus-Robert Müller
- BIFOLD – Berlin Institute for Foundations of Learning and Data, Berlin, Germany. Grégoire Montavon, Wojciech Samek & Klaus-Robert Müller
- Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute, Berlin, Germany. Wojciech Samek
- Department of Artificial Intelligence, Korea University, Seoul, Korea. Klaus-Robert Müller
- Max Planck Institut für Informatik, Saarbrücken, Germany. Klaus-Robert Müllerç
Get the work at https://link.springer.com/chapter/10.1007/978-3-031-04083-2_7