This unique book discusses machine understanding (MU). This new branch of classic machine perception research focuses on perception that leads to understanding and is based on the categories of sensory objects. In this approach the visual and non-visual knowledge, in the form of visual and non-visual concepts, is used in the complex reasoning process that leads to understanding. The book presents selected new concepts, such as perceptual transformations, within the machine understanding framework, and uses perceptual transformations to solve perceptual problems (visual intelligence tests) during understanding, where understanding is regarded as an ability to solve complex visual problems described in the authors’ previous books. Thanks to the uniqueness of the research topics covered, the book appeals to researchers from a wide range of disciplines, especially computer science, cognitive science and philosophy.

Introduces machine learning and its algorithmic paradigms, explaining the principles behind automated learning approaches and the considerations underlying their usage.

This is a comprehensive and thought-provoking exploration of the nature of machine understanding, its evaluation, and its implications. The book proposes a new framework, the Multifaceted Understanding Test Tool (MUTT), for assessing machine understanding across multiple dimensions, from language comprehension and logical reasoning to social intelligence and metacognition. Through a combination of philosophical analysis, technical exposition, and narrative thought experiments, the book delves into the frontiers of machine understanding, raising fundamental questions about the cognitive mechanisms and representations that enable genuine understanding in both human and machine minds. By probing the boundaries of artificial comprehension, the book aims to advance our theoretical grasp on the elusive notion of understanding and inform responsible development and deployment of AI technologies. In an era where Artificial Intelligence systems are becoming integral to our daily lives, a pressing question arises: Do these machines truly understand what they are doing, or are they merely sophisticated pattern matchers? "Understanding Machine Understanding" delves into this profound inquiry, exploring the depths of machine cognition and the essence of comprehension. Join Ken Clements and Claude 3 Opus on an intellectual journey that challenges conventional benchmarks like the Turing Test and introduces the innovative Multifaceted Understanding Test Tool (MUTT). This groundbreaking framework assesses AI's capabilities across language, reasoning, perception, and social intelligence, aiming to distinguish genuine understanding from mere imitation. Through philosophical analysis, technical exposition, and engaging narratives, this book invites readers to explore the frontiers of AI comprehension. Whether you're an AI researcher, philosopher, or curious observer, "Understanding Machine Understanding" offers a thought-provoking guide to the future of human-machine collaboration. Discover what it truly means for a machine to understand--and the implications for our shared future.

This is the third book presenting selected results of research on the further development of the shape understanding system (SUS) carried out by authors in the newly founded Queen Jadwiga Research Institute of Understanding. In this book the new term Machine Understanding is introduced referring to a new area of research aiming to investigate the possibility of building machines with the ability to understand. It is presented that SUS needs to some extent mimic human understanding and for this reason machines are evaluated according to the rules applied for the evaluation of human understanding. The book shows how to formulate problems and how it can be tested if the machine is able to solve these problems.

This book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

This book presents the selected results of research on the further development of the shape understanding system (SUS) described in our previous book titled “Shape Understanding System: the First Steps Toward the Visual Thinking Machines”. This is the second book that presents the results of research in the area of thinking and understanding carried out by authors in the newly founded the Queen Jadwiga Research Institute of Understanding. In this book, the new term knowledge implementation is introduced to denote the new method of the meaningful learning in the context of machine understanding. SUS ability to understand is related to the different categories of objects such as the category of visual objects, the category of sensory objects and the category of text objects. In this book, new terms and concepts are introduced in order to describe and explain some issues connected with SUS development. These terms are explained by referring to the content of our books and other our works rather than to existing literature in related areas of research. This book raises many questions that are discussed in the area of cognitive science or philosophy of mind.

Semantic agent systems are about the integration of the semantic Web, software agents, and multi-agent systems technologies. Like in the past (e.g. biology and informatics yielding bioinformatics) a whole new perspective is emerging with semantic agent systems. In this context, the semantic Web is a Web of semantically linked data which aims to enable man and machine to execute tasks in tandem. Here, software agents in a multi-agent system as delegates of humans are endowed with power to use semantically linked data. This edited book “Semantic Agent Systems: Foundations and Applications” proposes contributions on a wide range of topics on foundations and applications written by a selection of international experts. It first introduces in an accessible style the nature of semantic agent systems. Then it explores with numerous illustrations new frontiers in software agent technology. “Semantic Agent Systems: Foundations and Applications” is recommended for scientists, experts, researchers, and learners in the field of artificial intelligence, the semantic Web, software agents, and multi-agent systems technologies.