Abstract: "Although neural networks have been used to develop highly accurate classifiers in numerous real-world problem domains, the models they learn are notoriously difficult to understand. This thesis investigates the task of extracting comprehensible models from trained neural networks, thereby alleviating this limitation. The primary contribution of the thesis is an algorithm that overcomes the significant limitations of previous methods by taking a novel approach to the task of extracting comprehensible models from trained networks. This algorithm, called TREPAN, views the task as an inductive learning problem. Given a trained network, or any other learned model, TREPAN uses queries to induce a decision tree that approximates the function represented by the model. Unlike previous work in this area, TREPAN is broadly applicable as well as scalable to large networks and problems with high-dimensional input spaces. The thesis presents experiments that evaluate TREPAN by applying it to individual networks and to ensembles of neural networks trained in classification, regression, and reinforcement-learning domains. These experiments demonstrate that TREPAN is able to extract decision trees that are comprehensible, yet maintain high levels of fidelity to their respective networks. In problem domains in which neural networks provide superior predictive accuracy to conventional decision tree algorithms, the trees extracted by TREPAN also exhibit superior accuracy, but are comparable in terms of complexity, to the trees learned directly from the training data. A secondary contribution of this thesis is an algorithm, called BBP, that constructively induces simple neural networks. The motivation underlying this algorithm is similar to that for TREPAN: to learn comprehensible models in problem domains in which neural networks have an especially appropriate inductive bias. The BBP algorithm, which is based on a hypothesis-boosting method, learns perceptrons that have relatively few connections. This algorithm provides an appealing combination of strengths: it provides learnability guarantees for a fairly natural class of target functions; it provides good predictive accuracy in a variety of problem domains; and it constructs syntactically simple models, thereby facilitating human comprehension of what it has learned. These algorithms provide mechanisms for improving the understanding of what a trained neural network has learned."

This book presents the proceedings of the 24th European Conference on Artificial Intelligence (ECAI 2020), held in Santiago de Compostela, Spain, from 29 August to 8 September 2020. The conference was postponed from June, and much of it conducted online due to the COVID-19 restrictions. The conference is one of the principal occasions for researchers and practitioners of AI to meet and discuss the latest trends and challenges in all fields of AI and to demonstrate innovative applications and uses of advanced AI technology. The book also includes the proceedings of the 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020) held at the same time. A record number of more than 1,700 submissions was received for ECAI 2020, of which 1,443 were reviewed. Of these, 361 full-papers and 36 highlight papers were accepted (an acceptance rate of 25% for full-papers and 45% for highlight papers). The book is divided into three sections: ECAI full papers; ECAI highlight papers; and PAIS papers. The topics of these papers cover all aspects of AI, including Agent-based and Multi-agent Systems; Computational Intelligence; Constraints and Satisfiability; Games and Virtual Environments; Heuristic Search; Human Aspects in AI; Information Retrieval and Filtering; Knowledge Representation and Reasoning; Machine Learning; Multidisciplinary Topics and Applications; Natural Language Processing; Planning and Scheduling; Robotics; Safe, Explainable, and Trustworthy AI; Semantic Technologies; Uncertainty in AI; and Vision. The book will be of interest to all those whose work involves the use of AI technology.

It is our great pleasure to welcome you to the 11th International Conference on Neural Information Processing (ICONIP 2004) to be held in Calcutta. ICONIP 2004 is organized jointly by the Indian Statistical Institute (ISI) and Jadavpur University (JU). We are con?dent that ICONIP 2004, like the previous conf- ences in this series,will providea forum for fruitful interactionandthe exchange of ideas between the participants coming from all parts of the globe. ICONIP 2004 covers all major facets of computational intelligence, but, of course, with a primary emphasis on neural networks. We are sure that this meeting will be enjoyable academically and otherwise. We are thankful to the track chairs and the reviewers for extending their support in various forms to make a sound technical program. Except for a few cases, where we could get only two review reports, each submitted paper was reviewed by at least three referees, and in some cases the revised versions were againcheckedbythereferees. Wehad470submissionsanditwasnotaneasytask for us to select papers for a four-day conference. Because of the limited duration of the conference, based on the review reports we selected only about 40% of the contributed papers. Consequently, it is possible that some good papers are left out. We again express our sincere thanks to all referees for accomplishing a great job. In addition to 186 contributed papers, the proceedings includes two plenary presentations, four invited talks and 18 papers in four special sessions. The proceedings is organized into 26 coherent topical groups.

This volume contains selected tutorial and young scientist school papers of the 5th RAAI Summer School on Artificial Intelligence, held in July 2019 at Institute of Physics and Technology (MIPT) campus in Dolgoprudny, a suburb of Moscow, Russia. The 11 chapters in this volume present papers focusing on various important aspects of Multiagent systems; Behavior planning; Natural language processing; Modeling of reasoning; and Machine learning and data analysis.

Support vector machines (SVMs) are one of the most active research areas in machine learning. SVMs have shown good performance in a number of applications, including text and image classification. However, the learning capability of SVMs comes at a cost – an inherent inability to explain in a comprehensible form, the process by which a learning result was reached. Hence, the situation is similar to neural networks, where the apparent lack of an explanation capability has led to various approaches aiming at extracting symbolic rules from neural networks. For SVMs to gain a wider degree of acceptance in fields such as medical diagnosis and security sensitive areas, it is desirable to offer an explanation capability. User explanation is often a legal requirement, because it is necessary to explain how a decision was reached or why it was made. This book provides an overview of the field and introduces a number of different approaches to extracting rules from support vector machines developed by key researchers. In addition, successful applications are outlined and future research opportunities are discussed. The book is an important reference for researchers and graduate students, and since it provides an introduction to the topic, it will be important in the classroom as well. Because of the significance of both SVMs and user explanation, the book is of relevance to data mining practitioners and data analysts.

This book constitutes the refereed proceedings of the Second Mexican International Conference on Artificial Intelligence, MICAI 2002, held in Mérida, Yucatán, Mexico in April 2002. The 56 revised full papers presented were carefully reviewed and selected from more than 85 submissions from 17 countries. The papers are organized in topical sections on robotics and computer vision, heuristic search and optimization, speech recognition and natural language processing, logic, neural networks, machine learning, multi-agent systems, uncertainty management, and AI tools and applications.

Darwinian evolutionary theory is one of the most important theories in human history for it has equipped us with a valuable tool to understand the amazing world around us. There can be little surprise, therefore, that Evolutionary Computation (EC), inspired by natural evolution, has been so successful in providing high quality solutions in a large number of domains. EC includes a number of techniques, such as Genetic Algorithms, Genetic Programming, Evolution Strategy and Evolutionary Programming, which have been used in a diverse range of highly successful applications. This book brings together some of these EC applications in fields including electronics, telecommunications, health, bioinformatics, supply chain and other engineering domains, to give the audience, including both EC researchers and practitioners, a glimpse of this exciting rapidly evolving field.

Trust is a pervasive catalyst of human and business relationships that has inspired interest in researchers and practitioners alike. It has been shown to enhance engagement, communication, organizational performance, and online activities. Despite its role to cultivate cooperation, knowledge-sharing, and innovation, trust through digital means or even trust in digital media has presented new opportunities and challenges in society. Examples include a wider and faster dissemination of trust-influencing messages, and richer options of digital cues that engage, disrupt, or even transform how trust is formulated. Despite that, trust helps people to live through risky and uncertain situations, and the many capabilities enabled on the digital platforms have made the formation and sustaining of trust very different compared to traditional means. Trust in today’s digital environment plays an important role and is intertwined with concepts including reliability, quality, and privacy. This book aims to bring together the theory and practice of trust in the new digital era and will present theoretical and practical foundations. Trust is not given; we must work to build it, but it is a very fragile and intangible asset once built. It is easy to destroy and challenging to rebuild. Researchers, academics, and students in the fields of management, responsibility, and business ethics will gain knowledge on trust and related concepts, learn about the theoretical underpinnings of trust and how it sustains itself through digital dissemination, and explore empirically validated practice regarding trust and its related concepts.

Soft computing is the common name for a certain form of natural information processing that has its original form in biology, especially in the function of human brain. It is a discipline rooted in a group of technologies such as fuzzy logic, neural networks, chaos, genetic algorithms, probabilistic reasoning and learning algorithms. Today, soft computing has become an acknowledged concept; however, for a long time, such components of soft computing have been debated and individually developed.Since its beginning in 1990, the series of IIZUKA conferences has covered various kinds of technologies that constitute soft computing. This series has played a pioneering role in promoting the development of a symbiotic relationship between the various technologies of soft computing.At IIZUKA'98, the 5th International Conference on Soft Computing and Information/Intelligent Systems, new developments and results in this field were introduced and discussed by researchers from academic, governmental and industrial institutions around the world.This volume presents the opening lecture by Prof. Walter J Freeman, the keynote speech by Dr Gen Matsumoto, the plenary lectures by 5 eminent researchers and about 230 carefully selected papers drawn from more than 25 countries. It documents current research and in-depth studies on the fundamental aspects of soft computing and their practical applications.

"This book offers an outlook of the most recent works at the field of the Artificial Neural Networks (ANN), including theoretical developments and applications of systems using intelligent characteristics for adaptability"--Provided by publisher.