Explainable and Interpretable Models in Computer Vision and Machine Learning

Description

This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning. Research progress in computer vision and pattern recognition has led to a variety of modeling techniques with almost human-like performance. Although these models have obtained astounding results, they are limited in their explainability and interpretability: what is the rationale behind the decision made? what in the model structure explains its functioning? Hence, while good performance is a critical required characteristic for learning machines, explainability and interpretability capabilities are needed to take learning machines to the next step to include them in decision support systems involving human supervision. This book, written by leading international researchers, addresses key topics of explainability and interpretability, including the following: · Evaluation and Generalization in Interpretable Machine Learning · Explanation Methods in Deep Learning · Learning Functional Causal Models with Generative Neural Networks · Learning Interpreatable Rules for Multi-Label Classification · Structuring Neural Networks for More Explainable Predictions · Generating Post Hoc Rationales of Deep Visual Classification Decisions · Ensembling Visual Explanations · Explainable Deep Driving by Visualizing Causal Attention · Interdisciplinary Perspective on Algorithmic Job Candidate Search · Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions · Inherent Explainability Pattern Theory-based Video Event Interpretations Front Matter ....Pages i-xvii Front Matter ....Pages 1-1 Considerations for Evaluation and Generalization in Interpretable Machine Learning (Finale Doshi-Velez, Been Kim)....Pages 3-17 Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (Gabriëlle Ras, Marcel van Gerven, Pim Haselager)....Pages 19-36 Front Matter ....Pages 37-37 Learning Functional Causal Models with Generative Neural Networks (Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz, Michèle Sebag)....Pages 39-80 Learning Interpretable Rules for Multi-Label Classification (Eneldo Loza Mencía, Johannes Fürnkranz, Eyke Hüllermeier, Michael Rapp)....Pages 81-113 Structuring Neural Networks for More Explainable Predictions (Laura Rieger, Pattarawat Chormai, Grégoire Montavon, Lars Kai Hansen, Klaus-Robert Müller)....Pages 115-131 Front Matter ....Pages 133-133 Generating Post-Hoc Rationales of Deep Visual Classification Decisions (Zeynep Akata, Lisa Anne Hendricks, Stephan Alaniz, Trevor Darrell)....Pages 135-154 Ensembling Visual Explanations (Nazneen Fatema Rajani, Raymond J. Mooney)....Pages 155-172 Explainable Deep Driving by Visualizing Causal Attention (Jinkyu Kim, John Canny)....Pages 173-193 Front Matter ....Pages 195-195 Psychology Meets Machine Learning: Interdisciplinary Perspectives on Algorithmic Job Candidate Screening (Cynthia C. S. Liem, Markus Langer, Andrew Demetriou, Annemarie M. F. Hiemstra, Achmadnoer Sukma Wicaksana, Marise Ph. Born et al.)....Pages 197-253 Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions (Heysem Kaya, Albert Ali Salah)....Pages 255-275 On the Inherent Explainability of Pattern Theory-Based Video Event Interpretations (Sathyanarayanan N. Aakur, Fillipe D. M. de Souza, Sudeep Sarkar)....Pages 277-299