Explainable and Interpretable Models in Computer Vision and Machine Learning (The Springer Series on Challenges in Machine Learning)

Hugo Jair Escalante

ISBN 10: 3319981307 / ISBN 13: 9783319981307

Editore: Springer, 2019

Riguardo questo articolo

Gebraucht - Sehr gut - ungelesen,als Mängelexemplar gekennzeichnet, mit leichten Mängeln an Schnitt oder Einband durch Lager- oder Transportschaden -This book compiles leading research on the development of explainable and interpretable machine learning methods in the context of computer vision and machine learning.Springer Fachmedien Wiesbaden GmbH, Abraham-Lincoln-Str. 46, 65189 Wiesbaden 316 pp. Englisch.

Codice articolo INF1000251058

Dati bibliografici

• Titolo: Explainable and Interpretable Models in Computer Vision and Machine Learning (The Springer Series on Challenges in Machine Learning)
• Editore: Springer
• Data di pubblicazione: 2019
• Lingua: Inglese
• ISBN 10: 3319981307
• ISBN 13: 9783319981307
• Rilegatura: Gebundene Ausgabe
• Condizione: Sehr gut
• Dimensioni: 241 L x 161 A x 22 P (millimetri) 241 millimetri di larghezza per 161 millimetri di altezza per 22 millimetri di profondità
• Peso: 673 grammi

Descrizione articolo

Riassunto

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

Informazioni sull?autore

Placeholder.