00000nam a22000004a 4500 UP-8027390931311669105 Buklod 20250609131507.0 m |o d | cr ||||||||||| 250227s2023 xxu r |||| u|eng d 9780323960984 DLC DLC DLC rda eng eng DMLUC Q 325.73 E97 2023 Explainable deep learning AI methods and challenges edited by Jenny Benois-Pineau, Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, Talence, France, Romain, Bourqui, , Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, Talence, France, Dragutin Petkovic, San Francisco State University, CS Department, San Francisco, CA, United States, Georges Quenot, Univ. Grenble Alpes, CNRS, Grenoble INP, LIG, Grenoble, France. [2023] London, UK San Diego, CA Academic Press, an imprint of Elsevier xv, 329 pages illustrations (some color) 24 cm text rdacontent txt unmediated rdamedia n volume rdacarrier nc Includes bibliographical references and index. Introduction Explainable deep learning: concepts, methods, and new developments Compact visualization of DNN classification performances for interpretation and improvement Characterizing a scene recognition model by identifying the effect of input features via semantic-wise attribution A feature understanding method for explanation of image classification by convolutional neural networks Explainable deep learning for decrypting disease signatures in multiple sclerosis Explanation of CNN image classifiers with hiding parts Remove to improve? Explaining CNN classifier using association rule mining methods on time-series A methodology to compare XAI explanations on natural language processing Improving malware detection with explainable machine learning Explainability in medical image captioning User tests & techniques for the post-hoc explanation of deep learning Theoretical analysis of LIME - Conclusion Explainable Deep Learning AI: Methods and Challenges presents the latest works of leading researchers in the XAI area, offering an overview of the XAI area, along with several novel technical methods and applications that address explainability challenges for deep learning AI systems. The book overviews XAI and then covers a number of specific technical works and approaches for deep learning, ranging from general XAI methods to specific XAI applications, and finally, with user-oriented evaluation approaches. It also explores the main categories of explainable AI - deep learning, which become the necessary condition in various applications of artificial intelligence. The groups of methods such as back-propagation and perturbation-based methods are explained, and the application to various kinds of data classification are presented. Provides an overview of main approaches to Explainable Artificial Intelligence (XAI) in the Deep Learning realm, including the most popular techniques and their use, concluding with challenges and exciting future directions of XAI. Explores the latest developments in general XAI methods for Deep Learning. Explains how XAI for Deep Learning is applied to various domains like images, medicine and natural language processing. Provides an overview of how XAI systems are tested and evaluated, specially with real users, a critical need in XAI Artificial intelligence Deep learning (Machine learning) Explanation-based learning. Benois-Pineau, Jenny editor. Bourqui, Romain editor. Petkovic, Dragutin editor. Quenot, Georges editor. FO Printed UPD DSTC Q 325.73 E97 2023 Book