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 per...

Full description

Bibliographic Details
Corporate Author: SpringerLink (Online service)
Other Authors: Escalante, Hugo Jair (Editor, http://id.loc.gov/vocabulary/relators/edt), Escalera, Sergio (Editor, http://id.loc.gov/vocabulary/relators/edt), Guyon, Isabelle (Editor, http://id.loc.gov/vocabulary/relators/edt), Baró, Xavier (Editor, http://id.loc.gov/vocabulary/relators/edt), Güçlütürk, Yağmur (Editor, http://id.loc.gov/vocabulary/relators/edt), Güçlü, Umut (Editor, http://id.loc.gov/vocabulary/relators/edt), van Gerven, Marcel (Editor, http://id.loc.gov/vocabulary/relators/edt)
Format: Electronic eBook
Language:English
Published: Cham : Springer International Publishing : Imprint: Springer, 2018.
Edition:1st ed. 2018.
Series:The Springer Series on Challenges in Machine Learning,
Subjects:
Online Access:Full Text via HEAL-Link
Table of Contents:
  • 1 Considerations for Evaluation and Generalization in Interpretable Machine Learning
  • 2 Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges
  • 3 Learning Functional Causal Models with Generative Neural Networks
  • 4 Learning Interpretable Rules for Multi-label Classification
  • 5 Structuring Neural Networks for More Explainable Predictions
  • 6 Generating Post-Hoc Rationales of Deep Visual Classification Decisions
  • 7 Ensembling Visual Explanations
  • 8 Explainable Deep Driving by Visualizing Causal Action
  • 9 Psychology Meets Machine Learning: Interdisciplinary Perspectives on Algorithmic Job Candidate Screening
  • 10 Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions
  • 11 On the Inherent Explainability of Pattern Theory-based Video Event Interpretations. .