Neural Symbolic Cognitive Reasoning

This book explores why, regarding practical reasoning, humans are sometimes still faster than artificial intelligence systems. It is the first to offer a self-contained presentation of neural network models for many computer science logics.

Artificial Intelligence is concerned with producing devices that help or replace human beings in their daily activities. Neural-symbolic learning systems play a central role in this task by combining, and trying to benefit from, the advantages of both the neural and symbolic paradigms of artificial intelligence. This book provides a comprehensive introduction to the field of neural-symbolic learning systems, and an invaluable overview of the latest research issues in this area. It is divided into three sections, covering the main topics of neural-symbolic integration - theoretical advances in knowledge representation and learning, knowledge extraction from trained neural networks, and inconsistency handling in neural-symbolic systems. Each section provides a balance of theory and practice, giving the results of applications using real-world problems in areas such as DNA sequence analysis, power systems fault diagnosis, and software requirements specifications. Neural-Symbolic Learning Systems will be invaluable reading for researchers and graduate students in Engineering, Computing Science, Artificial Intelligence, Machine Learning and Neurocomputing. It will also be of interest to Intelligent Systems practitioners and anyone interested in applications of hybrid artificial intelligence systems.

Neuro-symbolic AI is an emerging subfield of Artificial Intelligence that brings together two hitherto distinct approaches. ”Neuro” refers to the artificial neural networks prominent in machine learning, ”symbolic” refers to algorithmic processing on the level of meaningful symbols, prominent in knowledge representation. In the past, these two fields of AI have been largely separate, with very little crossover, but the so-called “third wave” of AI is now bringing them together. This book, Neuro-Symbolic Artificial Intelligence: The State of the Art, provides an overview of this development in AI. The two approaches differ significantly in terms of their strengths and weaknesses and, from a cognitive-science perspective, there is a question as to how a neural system can perform symbol manipulation, and how the representational differences between these two approaches can be bridged. The book presents 17 overview papers, all by authors who have made significant contributions in the past few years and starting with a historic overview first seen in 2016. With just seven months elapsed from invitation to authors to final copy, the book is as up-to-date as a published overview of this subject can be. Based on the editors’ own desire to understand the current state of the art, this book reflects the breadth and depth of the latest developments in neuro-symbolic AI, and will be of interest to students, researchers, and all those working in the field of Artificial Intelligence.

A new proposal for integrating the employment of formal and empirical methods in the study of human reasoning. In Human Reasoning and Cognitive Science, Keith Stenning and Michiel van Lambalgen—a cognitive scientist and a logician—argue for the indispensability of modern mathematical logic to the study of human reasoning. Logic and cognition were once closely connected, they write, but were “divorced” in the past century; the psychology of deduction went from being central to the cognitive revolution to being the subject of widespread skepticism about whether human reasoning really happens outside the academy. Stenning and van Lambalgen argue that logic and reasoning have been separated because of a series of unwarranted assumptions about logic. Stenning and van Lambalgen contend that psychology cannot ignore processes of interpretation in which people, wittingly or unwittingly, frame problems for subsequent reasoning. The authors employ a neurally implementable defeasible logic for modeling part of this framing process, and show how it can be used to guide the design of experiments and interpret results.

Computational Architectures Integrating Neural and Symbolic Processes: A Perspective on the State of the Art focuses on a currently emerging body of research. With the reemergence of neural networks in the 1980s with their emphasis on overcoming some of the limitations of symbolic AI, there is clearly a need to support some form of high-level symbolic processing in connectionist networks. As argued by many researchers, on both the symbolic AI and connectionist sides, many cognitive tasks, e.g. language understanding and common sense reasoning, seem to require high-level symbolic capabilities. How these capabilities are realized in connectionist networks is a difficult question and it constitutes the focus of this book. Computational Architectures Integrating Neural and Symbolic Processes addresses the underlying architectural aspects of the integration of neural and symbolic processes. In order to provide a basis for a deeper understanding of existing divergent approaches and provide insight for further developments in this field, this book presents: (1) an examination of specific architectures (grouped together according to their approaches), their strengths and weaknesses, why they work, and what they predict, and (2) a critique/comparison of these approaches. Computational Architectures Integrating Neural and Symbolic Processes is of interest to researchers, graduate students, and interested laymen, in areas such as cognitive science, artificial intelligence, computer science, cognitive psychology, and neurocomputing, in keeping up-to-date with the newest research trends. It is a comprehensive, in-depth introduction to this new emerging field.

This book provides a broad overview of the key results and frameworks for various NSAO tasks as well as discussing important application areas. This book also covers neuro symbolic reasoning frameworks such as LNN, LTN, and NeurASP and learning frameworks. This would include differential inductive logic programming, constraint learning and deep symbolic policy learning. Additionally, application areas such a visual question answering and natural language processing are discussed as well as topics such as verification of neural networks and symbol grounding. Detailed algorithmic descriptions, example logic programs, and an online supplement that includes instructional videos and slides provide thorough but concise coverage of this important area of AI. Neuro symbolic artificial intelligence (NSAI) encompasses the combination of deep neural networks with symbolic logic for reasoning and learning tasks. NSAI frameworks are now capable of embedding prior knowledge in deep learning architectures, guiding the learning process with logical constraints, providing symbolic explainability, and using gradient-based approaches to learn logical statements. Several approaches are seeing usage in various application areas. This book is designed for researchers and advanced-level students trying to understand the current landscape of NSAI research as well as those looking to apply NSAI research in areas such as natural language processing and visual question answering. Practitioners who specialize in employing machine learning and AI systems for operational use will find this book useful as well.

If only it were possible to develop automated and trainable neural systems that could justify their behavior in a way that could be interpreted by humans like a symbolic system. The field of Neurosymbolic AI aims to combine two disparate approaches to AI; symbolic reasoning and neural or connectionist approaches such as Deep Learning. The quest to unite these two types of AI has led to the development of many innovative techniques which extend the boundaries of both disciplines. This book, Compendium of Neurosymbolic Artificial Intelligence, presents 30 invited papers which explore various approaches to defining and developing a successful system to combine these two methods. Each strategy has clear advantages and disadvantages, with the aim of most being to find some useful middle ground between the rigid transparency of symbolic systems and the more flexible yet highly opaque neural applications. The papers are organized by theme, with the first four being overviews or surveys of the field. These are followed by papers covering neurosymbolic reasoning; neurosymbolic architectures; various aspects of Deep Learning; and finally two chapters on natural language processing. All papers were reviewed internally before publication. The book is intended to follow and extend the work of the previous book, Neuro-symbolic artificial intelligence: The state of the art (IOS Press; 2021) which laid out the breadth of the field at that time. Neurosymbolic AI is a young field which is still being actively defined and explored, and this book will be of interest to those working in AI research and development.

"This book combines the AI and cognitive sciences approaches. In combing insights from each of the separate fields, the book gives a unified view of knowledge representation." -- Preface.