Seminar
Seminar: Explainable Machine Learning
Content
Current publications on machine learning / computer vision are covered in this seminar. In particular, topics from the area of explainable machine learning (in particular vision and language based deep learning, attention models, transformers) are in focus.
This is a Master's level course. Since these topics are very complex, prior participation in at least one of the following lectures is required:
- Deep Learning
- Probabilistic Machine Learning
- Statistical Machine Learning
Organisation
The schedule of the seminar is as follows:
- November 4th, 2-6pm (Slides)
- November 11th, 2-6pm
- November 18th, 2-6pm
- November 25th, 2-6pm
- December 2, 2-6pm
- December 9, 2-6pm
- December 16, 2-6pm
All seminars will take place on zoom. All the accepted participants will receive the zoom link on their email that they used in ILIAS.
The course awards 3 LP Credits.
Requirements
A successful participation in the seminar includes:
- Active participation in the entire event: We have 70% attendance policy for this seminar. You need to attend at least 5 of the 7 sessions.
- Short presentation on November 11th or 18th (10 minutes talk, 5 min questions)
- Presentation on November 25th, December 6, 9 or 16th (20 minutes talk, 10 minutes questions) on a selected topic
Topics to be covered
Interpretability in psychology and cognitive sciences:
- Explanation and Understanding, Frank C. Keil, Annu Rev Psychol.: 2006
- The structure and function of explanations, Tania Lombrozo, Trends in Cognitive Sciences, 2006
- Rational quantitative attribution of beliefs, desires and percepts in human mentalizing, Baker etal, Nature Human Behaviour 2017
- Explanation in Artificial Intelligence: Insights from the social sciences, Tim Miller, Artificial Intelligence, Elsevier, 2019
Machine Attention in Natural Language Processing and Computer Vision:
- Multimodal Explanations: Justifying Decisions and Pointing to the Evidence, Park etal, CVPR 2018
- Attention is not Explanation, Jain and Wallace, NAACL 2019
- Attention is not not Explanation, Wiegreffe and Pinter, EMNLP 2019
- Attribute Prototype Network for Zero-Shot Learning, Xu etal, NeurIPS 2020
- Textual Explanations for Self-Driving Vehicles, Kim etal, ECCV 2018
Human attention:
Textual and visual explanations for natural image data:
- Generating Visual Explanations, Hendricks etal, ECCV 2016
- Grounding Visual Explanations, Hendricks etal, ECCV 2018
- Visual Dialog, Das etal, CVPR 2017
- Machine Theory of Mind, Rabinowitz et al., ICML 2018
- Modeling Conceptual Understanding in Image Reference Games, Corona etal, NeurIPS 2019
Textual and visual explanations for medical image data:
Compositional Learning:
- Attributes as operators: factorizing unseen attribute-object compositions, Tushar and Grauman, ECCV 2018
- Task-driven modular networks for zero-shot compositional learning, Purushwalkam etal, ICCV 2019
- A causal view of compositional zero-shot recognition, Atzman etal, NeurIPS 2020
- LiveSketch: Query Perturbations for Guided Sketch-based Visual Search, Collomosse etal, CVPR 2019
- Self-Challenging Improves Cross-Domain Generalization, Huang etal, ECCV 2020
Combining classical decision trees and deep learning:
Registration
The registration opens on October 5th via ILIAS.