Explainable Neural Networks Based On Fuzzy Logic And Multi Criteria Decision Tools

The research presented in this book shows how combining deep neural networks with a special class of fuzzy logical rules and multi-criteria decision tools can make deep neural networks more interpretable – and even, in many cases, more efficient. Fuzzy logic together with multi-criteria decision-making tools provides very powerful tools for modeling human thinking. Based on their common theoretical basis, we propose a consistent framework for modeling human thinking by using the tools of all three fields: fuzzy logic, multi-criteria decision-making, and deep learning to help reduce the black-box nature of neural models; a challenge that is of vital importance to the whole research community.

This book constitutes the second part of refereed proceedings of the 5th Computational Methods in Systems and Software 2021 (CoMeSySo 2021) proceedings. The real-world problems related to data science and algorithm design related to systems and software engineering are presented in this papers. Furthermore, the basic research’ papers that describe novel approaches in the data science, algorithm design and in systems and software engineering are included. The CoMeSySo 2021 conference is breaking the barriers, being held online. CoMeSySo 2021 intends to provide an international forum for the discussion of the latest high-quality research results

This book is focused on connecting two interesting research areas, mathematics and computational intelligence, by means of appealing contributions devoted to give solutions to different challenges of the current technological age. It continues the collection of articles dealing with the important and efficient combination of these both areas, with a stress of fuzzy systems and fuzzy logic. It also includes relevant papers on the development and application of mathematics, artificial intelligence, and automatic reasoning tools to Digital Forensics, which have been developed within the framework of the COST Action DigForASP-CA17124 (digforasp.uca.es).

The development of “intelligent” systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to “intelligent” machines. For sensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner. The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.

This book contains the papers presented at the 20th UK Workshop on Computational Intelligence (UKCI 2021), held virtually by Aberystwyth University, 8–10th September 2021. This marks the 20th anniversary of UKCI; a testament to the increasing role and importance of Computational Intelligence (CI) and the continuing interest in its development. UKCI provides a forum for the academic community and industry to share ideas and experience in this field. EDMA 2021, the 4th International Engineering Data- and Model-Driven Applications workshop, is also incorporated and held in conjunction with UKCI 2021. Paper submissions were invited in the areas of fuzzy systems, neural networks, evolutionary computation, machine learning, data mining, cognitive computing, intelligent robotics, hybrid methods, deep learning and applications of CI.

This book provides comprehensive introduction to a consortium of technologies underlying soft computing, an evolving branch of computational intelligence. The constituent technologies discussed comprise neural networks, fuzzy logic, genetic algorithms, and a number of hybrid systems which include classes such as neuro-fuzzy, fuzzy-genetic, and neuro-genetic systems. The hybridization of the technologies is demonstrated on architectures such as Fuzzy-Back-propagation Networks (NN-FL), Simplified Fuzzy ARTMAP (NN-FL), and Fuzzy Associative Memories. The book also gives an exhaustive discussion of FL-GA hybridization. Every architecture has been discussed in detail through illustrative examples and applications. The algorithms have been presented in pseudo-code with a step-by-step illustration of the same in problems. The applications, demonstrative of the potential of the architectures, have been chosen from diverse disciplines of science and engineering. This book with a wealth of information that is clearly presented and illustrated by many examples and applications is designed for use as a text for courses in soft computing at both the senior undergraduate and first-year post-graduate engineering levels. It should also be of interest to researchers and technologists desirous of applying soft computing technologies to their respective fields of work.

This book constitutes the refereed proceedings of the 7th International Conference on Theory and Practice of Natural Computing, TPNC 2017, held in Dublin, Ireland, in December 2018. The 35 full papers presented in this book, together with one invited talk, were carefully reviewed and selected from 69 submissions. The papers are organized around the following topical sections: applications of natural computing as algorithms, bioinformatics, control, cryptography, design, economics. The more theoretical contributions handle with artificial chemistry, artificial immune systems, artificial life, cellular automata, cognitive computing, cognitive engineering, cognitive robotics, collective behaviour, complex systems, computational intelligence, computational social science, computing with words, developmental systems, DNA computing, DNA nanotechnology, evolutionary algorithms, evolutionary computing, evolutionary game theory, fractal geometry, fuzzy control, fuzzy logic, fuzzy sets, fuzzy systems, genetic algorithms, genetic programming, granular computing, heuristics, intelligent agents, intelligent systems, machine intelligence, molecular programming, neural computing, neural networks, quantum communication, quantum computing, rough sets, self-assembly.

Machine learning and artificial intelligence are already widely applied to facilitate our daily lives, as well as scientific research, but with the world currently facing a global COVID-19 pandemic, their capacity to provide an important tool to support those searching for a way to combat the novel corona virus has never been more important. This book presents the proceedings of the International Conference on Machine Learning and Intelligent Systems (MLIS 2020), which was due to be held in Seoul, Korea, from 25-28 October 2020, but which was delivered as an online conference on the same dates due to COVID-19 restrictions. MLIS 2020 was the latest in a series of annual conferences that aim to provide a platform for exchanging knowledge about the most recent scientific and technological advances in the field of machine learning and intelligent systems. The annual conference also strengthens links within the scientific community in related research areas. The book contains 53 papers, selected from more than 160 submissions and presented at MLIS 2020. Selection was based on the results of review and scored on: originality, scientific/practical significance, compelling logical reasoning and language. Topics covered include: data mining, image processing, neural networks, human health, natural language processing, video processing, computational intelligence, expert systems, human-computer interaction, deep learning, and robotics. Offering a current overview of research and developments in machine learning and artificial intelligence, the book will be of interest to all those working in the field.