Explainable and Interpretable Models in Computer Vision and Machine Learning

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