دانلود کتاب هوش مصنوعی یادگیری عمیق قابل توضیح

Artificial Intelligence (AI) techniques, especially those based on Deep Learning (DL), have become extremely effective on a very large variety of tasks, sometimes performing even better than human experts. However, they also have a number of problems: they generally operate in mostly opaque and/or intractable ways, their very good performance is only statistical and they can fail even on apparently obvious cases, they can make biased decisions, and they can be quite easily manipulated through adversarial attacks, to cite a few. These limitations prevent their adoption in applications of great economic or societal interest, especially for critical or sensible applications like autonomous driving, medical diagnosis, or loan approvals. Considering this, a lot of research has been conducted in order to increase the trustworthiness of DL-based AI systems by providing explanations understandable by human users for the decisions made by these systems. The aim of this book is to present recent and original contributions covering the main approaches in the domain of explainable DL, either for expert or for layman users. Two main types of approaches are presented: the “post hoc” or “model agnostic” ones, in which the operation of an already available “black box” system is modeled and explained, and the intrinsic ones, in which systems are specifically designed as “white boxes” with an interpretable mode of operation. This book is a follow-up of a very successful Workshop “Explainable Deep Learning-AI” which we have organized at ICPR’2020 IAPR and IEEE conference making a large tour of ongoing research in the field. The question of the explainability is addressed in a variety of media domains, including images, text, temporal series, and tabular data. The difficult and important question of the evaluation of explanation methods is also specifically addressed in two chapters. Finally, still open challenges are mentioned in the concluding chapter.