Explainable and Interpretable Models in Computer Vision and Machine Learning

null

74,95 €

inkl. MwSt. und Versand · Lieferzeit 1–2 Werktage

Gesetzliche Gewährleistung: 2 Jahre · Details

Nur noch 1 verfügbar

Beschreibung

<div><p>This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning.</p><p>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.</p><p>This book, written by leading international researchers, addresses key topics of explainability and interpretability, including the following:</p><p>· Evaluation and Generalization in Interpretable Machine Learning</p><p>· Explanation Methods in Deep Learning</p><p>· Learning Functional Causal Models with Generative Neural Networks</p><p>· Learning Interpreatable Rules for Multi-Label Classification</p><p>· Structuring Neural Networks for More Explainable Predictions</p><p>· Generating Post Hoc Rationales of Deep Visual Classification Decisions</p><p>· Ensembling Visual Explanations</p><p>· Explainable Deep Driving by Visualizing Causal Attention</p><p>· Interdisciplinary Perspective on Algorithmic Job Candidate Search</p><p>· Multimodal Personality Trait Analysis for Explainable Modeling of Job Interview Decisions</p><p>· Inherent Explainability Pattern Theory-based Video Event Interpretations</p></div>

Artikeldetails

EAN

9783319981307

Sprache

Englisch

Einband / Art

Bundle

Maße

241 x 161 x 22 mm

Erscheinungsjahr

2019

Verlag / Hersteller

Springer-Verlag GmbH