Includes bibliographical references and index.

Graph augmentation using matching-graphs -- Controlling topology preserving graph pyramids -- A sensor-independent multi-modal fusion scheme for human activity recognition -- Metrics for saliency map evaluation of deep learning explanation methods -- Efficient segmentation of e-waste devices with deep learning for robotic recycling -- Shop signboard detection using the ShoS dataset -- Self-distilled self-supervised monocular depth estimation -- An encoder-decoder approach to offline handwritten mathematical expression recognition with residual attention -- A complexity analysis on the general feasibility of patch-based adversarial attacks on semantic segmentation problems -- Sentiment and word cloud analysis of tweets related to COVID-19 vaccines before, during, and after the second wave in India -- Reinforcement learning and sequential QAP-based graph matching for semantic segmentation of images -- FEM and multi-layered FEM: feature explanation methods with statistical filtering of important features.

"The unique compendium covers a wide range of recent advanced contributions in Pattern Recognition and Artificial Intelligence, both in theoretical aspects and applications. It highlights the importance of Deep Learning in various domains, from acquisition to Decision Making. Written by world renowned contributors, this high-quality research works presents case studies that can potentially help them find approaches and resources to address their scientific problems. It is a useful reference text for professionals, researchers, academics and graduate students in the fields of artificial intelligence, machine learning and deep learning"-- Publisher's website.

Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader.