This edited collection describes recent progress on lazy learning, a branch of machine learning concerning algorithms that defer the processing of their inputs, reply to information requests by combining stored data, and typically discard constructed replies. It is the first edited volume in AI on this topic, whose many synonyms include `instance-based', `memory-based'. `exemplar-based', and `local learning', and whose topic intersects case-based reasoning and edited k-nearest neighbor classifiers. It is intended for AI researchers and students interested in pursuing recent progress in this branch of machine learning, but, due to the breadth of its contributions, it should also interest researchers and practitioners of data mining, case-based reasoning, statistics, and pattern recognition.

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.

The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.

Features:

Contributes to the topic of explainable artificial intelligence (XAI) Focuses on the XAI subtopic of explainable agency Includes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.

The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.

Features:

Contributes to the topic of explainable artificial intelligence (XAI) Focuses on the XAI subtopic of explainable agency Includes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.Features:Contributes to the topic of explainable artificial intelligence (XAI)Focuses on the XAI subtopic of explainable agencyIncludes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.Features:Contributes to the topic of explainable artificial intelligence (XAI)Focuses on the XAI subtopic of explainable agencyIncludes an introductory chapter, a survey, and five other original contributions

This book constitutes the refereed proceedings of the 25th International Conference on Case-Based Reasoning Research and Development, ICCBR 2017,  held in Trondheim, Norway, in June 2017. The 27 full papers presented together with 3 keynote presentations were carefully reviewed and selected from 38 submissions. The theme of ICCBR-2017, "Analogy for Reuse", was highlighted in several events.These papers, which are included in the proceedings, address many themes related to the theory and application of case-based reasoning, analogical reasoning, CBR and Deep Learning, CBR in the Health Sciences, Computational Analogy, and Process-Oriented CBR.

This book constitutes the refereed proceedings of the 25th International Conference on Case-Based Reasoning Research and Development, ICCBR 2017,  held in Trondheim, Norway, in June 2017. 

The 27 full papers presented together with 3 keynote presentations were carefully reviewed and selected from 38 submissions. The theme of ICCBR-2017, "Analogy for Reuse", was highlighted in several events.

These papers, which are included in the proceedings, address many themes related to the theory and application of case-based reasoning, analogical reasoning, CBR and Deep Learning, CBR in the Health Sciences, Computational Analogy, and Process-Oriented CBR.

The 2001 International Conference on Case-Based Reasoning (ICCBR 2001, www.iccbr.org/iccbr01), the fourth in the biennial ICCBR series (1995 in Sesimbra, Portugal; 1997 in Providence, Rhode Island (USA); 1999 in Seeon, Germany), was held during 30 July – 2 August 2001 in Vancouver, Canada. ICCBR is the premier international forum for researchers and practitioners of case based reasoning (CBR). The objectives of this meeting were to nurture significant, relevant advances made in this field (both in research and application), communicate them among all attendees, inspire future advances, and continue to support the vision that CBR is a valuable process in many research disciplines, both computational and otherwise. ICCBR 2001 was the first ICCBR meeting held on the Pacific coast, and we used the setting of beautiful Vancouver as an opportunity to enhance participation from the Pacific Rim communities, which contributed 28% of the submissions. During this meeting, we were fortunate to host invited talks by Ralph Bergmann, Ken Forbus, Jaiwei Han, Ramon López de Mántaras, and Manuela Veloso. Their contributions ensured a stimulating meeting; we thank them all.

The 2001 International Conference on Case-Based Reasoning (ICCBR 2001, www.iccbr.org/iccbr01), the fourth in the biennial ICCBR series (1995 in Sesimbra, Portugal; 1997 in Providence, Rhode Island (USA); 1999 in Seeon, Germany), was held during 30 July – 2 August 2001 in Vancouver, Canada. ICCBR is the premier international forum for researchers and practitioners of case based reasoning (CBR). The objectives of this meeting were to nurture significant, relevant advances made in this field (both in research and application), communicate them among all attendees, inspire future advances, and continue to support the vision that CBR is a valuable process in many research disciplines, both computational and otherwise. ICCBR 2001 was the first ICCBR meeting held on the Pacific coast, and we used the setting of beautiful Vancouver as an opportunity to enhance participation from the Pacific Rim communities, which contributed 28% of the submissions. During this meeting, we were fortunate to host invited talks by Ralph Bergmann, Ken Forbus, Jaiwei Han, Ramon López de Mántaras, and Manuela Veloso. Their contributions ensured a stimulating meeting; we thank them all.

This edited collection describes recent progress on lazy learning, a branch of machine learning concerning algorithms that defer the processing of their inputs, reply to information requests by combining stored data, and typically discard constructed replies. It is the first edited volume in AI on this topic, whose many synonyms include `instance-based', `memory-based'. `exemplar-based', and `local learning', and whose topic intersects case-based reasoning and edited k-nearest neighbor classifiers. It is intended for AI researchers and students interested in pursuing recent progress in this branch of machine learning, but, due to the breadth of its contributions, it should also interest researchers and practitioners of data mining, case-based reasoning, statistics, and pattern recognition.

This edited collection describes recent progress on lazy learning, a branch of machine learning concerning algorithms that defer the processing of their inputs, reply to information requests by combining stored data, and typically discard constructed replies. It is the first edited volume in AI on this topic, whose many synonyms include `instance-based', `memory-based'. `exemplar-based', and `local learning', and whose topic intersects case-based reasoning and edited k-nearest neighbor classifiers. It is intended for AI researchers and students interested in pursuing recent progress in this branch of machine learning, but, due to the breadth of its contributions, it should also interest researchers and practitioners of data mining, case-based reasoning, statistics, and pattern recognition.

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.

The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.

Features:

Contributes to the topic of explainable artificial intelligence (XAI) Focuses on the XAI subtopic of explainable agency Includes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.

The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.

Features:

Contributes to the topic of explainable artificial intelligence (XAI) Focuses on the XAI subtopic of explainable agency Includes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.Features:Contributes to the topic of explainable artificial intelligence (XAI)Focuses on the XAI subtopic of explainable agencyIncludes an introductory chapter, a survey, and five other original contributions

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.Features:Contributes to the topic of explainable artificial intelligence (XAI)Focuses on the XAI subtopic of explainable agencyIncludes an introductory chapter, a survey, and five other original contributions

This book constitutes the refereed proceedings of the 25th International Conference on Case-Based Reasoning Research and Development, ICCBR 2017,  held in Trondheim, Norway, in June 2017. The 27 full papers presented together with 3 keynote presentations were carefully reviewed and selected from 38 submissions. The theme of ICCBR-2017, "Analogy for Reuse", was highlighted in several events.These papers, which are included in the proceedings, address many themes related to the theory and application of case-based reasoning, analogical reasoning, CBR and Deep Learning, CBR in the Health Sciences, Computational Analogy, and Process-Oriented CBR.

This book constitutes the refereed proceedings of the 25th International Conference on Case-Based Reasoning Research and Development, ICCBR 2017,  held in Trondheim, Norway, in June 2017. 

The 27 full papers presented together with 3 keynote presentations were carefully reviewed and selected from 38 submissions. The theme of ICCBR-2017, "Analogy for Reuse", was highlighted in several events.

These papers, which are included in the proceedings, address many themes related to the theory and application of case-based reasoning, analogical reasoning, CBR and Deep Learning, CBR in the Health Sciences, Computational Analogy, and Process-Oriented CBR.

The 2001 International Conference on Case-Based Reasoning (ICCBR 2001, www.iccbr.org/iccbr01), the fourth in the biennial ICCBR series (1995 in Sesimbra, Portugal; 1997 in Providence, Rhode Island (USA); 1999 in Seeon, Germany), was held during 30 July – 2 August 2001 in Vancouver, Canada. ICCBR is the premier international forum for researchers and practitioners of case based reasoning (CBR). The objectives of this meeting were to nurture significant, relevant advances made in this field (both in research and application), communicate them among all attendees, inspire future advances, and continue to support the vision that CBR is a valuable process in many research disciplines, both computational and otherwise. ICCBR 2001 was the first ICCBR meeting held on the Pacific coast, and we used the setting of beautiful Vancouver as an opportunity to enhance participation from the Pacific Rim communities, which contributed 28% of the submissions. During this meeting, we were fortunate to host invited talks by Ralph Bergmann, Ken Forbus, Jaiwei Han, Ramon López de Mántaras, and Manuela Veloso. Their contributions ensured a stimulating meeting; we thank them all.

The 2001 International Conference on Case-Based Reasoning (ICCBR 2001, www.iccbr.org/iccbr01), the fourth in the biennial ICCBR series (1995 in Sesimbra, Portugal; 1997 in Providence, Rhode Island (USA); 1999 in Seeon, Germany), was held during 30 July – 2 August 2001 in Vancouver, Canada. ICCBR is the premier international forum for researchers and practitioners of case based reasoning (CBR). The objectives of this meeting were to nurture significant, relevant advances made in this field (both in research and application), communicate them among all attendees, inspire future advances, and continue to support the vision that CBR is a valuable process in many research disciplines, both computational and otherwise. ICCBR 2001 was the first ICCBR meeting held on the Pacific coast, and we used the setting of beautiful Vancouver as an opportunity to enhance participation from the Pacific Rim communities, which contributed 28% of the submissions. During this meeting, we were fortunate to host invited talks by Ralph Bergmann, Ken Forbus, Jaiwei Han, Ramon López de Mántaras, and Manuela Veloso. Their contributions ensured a stimulating meeting; we thank them all.

This edited collection describes recent progress on lazy learning, a branch of machine learning concerning algorithms that defer the processing of their inputs, reply to information requests by combining stored data, and typically discard constructed replies. It is the first edited volume in AI on this topic, whose many synonyms include `instance-based', `memory-based'. `exemplar-based', and `local learning', and whose topic intersects case-based reasoning and edited k-nearest neighbor classifiers. It is intended for AI researchers and students interested in pursuing recent progress in this branch of machine learning, but, due to the breadth of its contributions, it should also interest researchers and practitioners of data mining, case-based reasoning, statistics, and pattern recognition.