Explainable and Interpretable Models in Computer Vision and Machine Learning
Компьютерная литература / Программирование
Основная информация:
Название: Explainable and Interpretable Models in Computer Vision and Machine Learning
Жанр: Нет
Автор: Hugo Jair Escalante, Sergio Escalera
Год выпуска: 2018
Формат: PDF
Размер: 10.1 MB
ISBN: 945874992245
Язык: Английский
СКАЧАТЬ Explainable and Interpretable Models in Computer Vision and Machine Learning БЕСПЛАТНО EPUB - DOC - DJVU - RTF - PDFОписание: 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.
"Too much of a black box to me”. That is an often heard and long-standing criticism of data-driven machine learning methods, in general, and (deep) neural networks, in particular. Nevertheless, astounding results have been obtained with these black boxes.
Interestingly, one could argue that this is, to a large extent, not in spite of but rather thanks to their black box nature: researchers no longer aim at full control over the model intrinsics, a common practice in the hand-crafted features era. Instead, the data leads the way, optimising the whole system in an end-to-end manner for the task at hand, yielding superior results.
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