Explanation Based Neural Network Learning

Author: Sebastian Thrun
Publisher: Springer Science & Business Media
ISBN: 9781461313816
Size: 13.55 MB
Format: PDF, Docs
View: 50

Lifelong learning addresses situations in which a learner faces a series of different learning tasks providing the opportunity for synergy among them. Explanation-based neural network learning (EBNN) is a machine learning algorithm that transfers knowledge across multiple learning tasks. When faced with a new learning task, EBNN exploits domain knowledge accumulated in previous learning tasks to guide generalization in the new one. As a result, EBNN generalizes more accurately from less data than comparable methods. Explanation-Based Neural Network Learning: A Lifelong Learning Approach describes the basic EBNN paradigm and investigates it in the context of supervised learning, reinforcement learning, robotics, and chess. `The paradigm of lifelong learning - using earlier learned knowledge to improve subsequent learning - is a promising direction for a new generation of machine learning algorithms. Given the need for more accurate learning methods, it is difficult to imagine a future for machine learning that does not include this paradigm.' From the Foreword by Tom M. Mitchell.

Recent Advances In Robot Learning

Author: Judy A. Franklin
Publisher: Springer Science & Business Media
ISBN: 9781461304715
Size: 15.53 MB
Format: PDF
View: 70

Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. Since robot learning involves decision making, there is an inherent active learning issue. Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. On the other hand, machine learning is also highly attractive to robotics. There is a great variety of open problems in robotics that defy a static, hand-coded solution. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3).

Adaptive Computing In Design And Manufacture V

Author: Ian Parmee
Publisher: Springer Science & Business Media
ISBN: 1852336056
Size: 17.31 MB
Format: PDF, Kindle
View: 52

The Adaptive Computing in Design and Manufacture Conference series is now in its tenth year and has become a well-established, application-oriented meeting recognised by several UK Engineering Institutions and the International Society of Genetic and Evolutionary Computing. The main theme of the conference again relates to the integration of evolutionary and adaptive computing technologies with design and manufacturing processes whilst also taking into account complementary advanced computing technologies. Evolutionary and adaptive computing techniques continue to increase their penetration of industrial and commercial practice as their powerful search, exploration and optimisation capabilities become ever more apparent. The last two years have seen a very significant increase in the development of commercial software tools utilising adaptive computing technologies and the emergence of related commercial research and consultancy organisations supporting the introduction of best practice in terms of industrial utilisation. Adaptive Computing in Design and Manufacture V is comprised of selected papers that cover a diverse set of industrial application areas including: engineering design and design environments, manufacturing process design, scheduling and control, electronic circuit design, fault detection. Various aspects of search and optimisation such as multi-objective and constrained optimisation are also investigated in the context of integration with industrial processes. In addition to evolutionary computing techniques, both neural-net and agent-based technologies play a role in a number of contributions. This collection of papers will be of particular interest to both industrial researchers and practitioners in addition to the academic research communities of engineering, operational research and computer science.

Micai 2000 Advances In Artificial Intelligence

Author: Osvaldo Cairo
Publisher: Springer Science & Business Media
ISBN: 9783540673545
Size: 19.42 MB
Format: PDF, ePub, Mobi
View: 88

This book constitutes the refereed proceedings of the Mexican International Conference on Artificial Intelligence, MICAI 2000, held in Acapulco, Mexico, in April 2000. The 60 revised full papers presented with six invited contributions were carefully reviewed and selected from a total of 163 submissions from 17 countries. The book is divided into sections on knowledge representation and reasoning, robotics and computer vision, machine learning, neural networks, knowledge-based systems, speech recognition and natural language, multiagent systems, reasoning under uncertainty, and intelligent tutoring systems.

Neural Symbolic Learning Systems

Author: Artur S. d'Avila Garcez
Publisher: Springer Science & Business Media
ISBN: 9781447102113
Size: 16.17 MB
Format: PDF, ePub
View: 64

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.

Learning To Learn

Author: Sebastian Thrun
Publisher: Springer Science & Business Media
ISBN: 9781461555292
Size: 14.93 MB
Format: PDF, ePub, Docs
View: 75

Over the past three decades or so, research on machine learning and data mining has led to a wide variety of algorithms that learn general functions from experience. As machine learning is maturing, it has begun to make the successful transition from academic research to various practical applications. Generic techniques such as decision trees and artificial neural networks, for example, are now being used in various commercial and industrial applications. Learning to Learn is an exciting new research direction within machine learning. Similar to traditional machine-learning algorithms, the methods described in Learning to Learn induce general functions from experience. However, the book investigates algorithms that can change the way they generalize, i.e., practice the task of learning itself, and improve on it. To illustrate the utility of learning to learn, it is worthwhile comparing machine learning with human learning. Humans encounter a continual stream of learning tasks. They do not just learn concepts or motor skills, they also learn bias, i.e., they learn how to generalize. As a result, humans are often able to generalize correctly from extremely few examples - often just a single example suffices to teach us a new thing. A deeper understanding of computer programs that improve their ability to learn can have a large practical impact on the field of machine learning and beyond. In recent years, the field has made significant progress towards a theory of learning to learn along with practical new algorithms, some of which led to impressive results in real-world applications. Learning to Learn provides a survey of some of the most exciting new research approaches, written by leading researchers in the field. Its objective is to investigate the utility and feasibility of computer programs that can learn how to learn, both from a practical and a theoretical point of view.