Sebastian Thrun

Lorien Pratt

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.

Learning to Learn

Michael Montemerlo

This monograph describes a new family of algorithms for the simultaneous localization and mapping (SLAM) problem in robotics, called FastSLAM. The FastSLAM-type algorithms have enabled robots to acquire maps of unprecedented size and accuracy, in a number of robot application domains and have been successfully applied in different dynamic environments, including a solution to the problem of people tracking.

A Scalable Method for the Simultaneous Localization and Mapping Problem in Robotics

FastSLAM

Hajime Asama

Erwin Prassler

Shin'ichi Yuta

Takashi Tsubouchi

This unique collection is the post-conference proceedings of the 4th "International Conference on Field and Service Robotics" (FSR). This book has authoritative contributors and presents current developments and new directions in field and service robotics. The book represents a cross-section of the current state of robotics research from one particular aspect: field and service applications, and how they reflect on the theoretical basis of subsequent developments.

Recent Advances in Research and Applications

Field and Service Robotics

Rodney A. Brooks

Hugh Durrant-Whyte

This volume contains 50 papers presented at the 12th International Symposium of Robotics Research, which took place October 2005 in San Francisco, CA. Coverage includes: physical human-robot interaction, humanoids, mechanisms and design, simultaneous localization and mapping, field robots, robotic vision, robot design and control, underwater robotics, learning and adaptive behavior, networked robotics, and interfaces and interaction.

Results of the 12th International Symposium ISRR

Robotics Research

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.

a Lifelong Learning Approach

Explanation-Based Neural Network Learning

Tom Mitchell

Carnegie-Mellon University. Computer Science Dept

Kamal Nigam

Andrew MacCallum

Abstract: "This paper shows that the accuracy of learned text classifiers can be improved by augmenting a small number of labeled training documents with a large pool of unlabeled documents. This is significant because in many important text classification problems obtaining classification labels is expensive, while large quantities of unlabeled documents are readily available. We present a theoretical argument showing that, under common assumptions, unlabeled data contain information about the target function. We then introduce an algorithm for learning from labeled and unlabeled text, based on the combination of Expectation-Maximization with a naive Bayes classifier. The algorithm first trains a classifier using the available labeled documents, and probabilistically labels the unlabeled documents. It then trains a new classifier using the labels for all the documents, and iterates. Experimental results, obtained using text from three different real-world tasks, show that the use of unlabeled data reduces classification error by up to 30%."

Using EM to Classify Text from Labeled and Unlabeled Documents

Chris Guillebeau

Warren Berger

John Maeda

Seth Godin

Julie Zhuo

Scott Belsky

Shane Snow

Jocelyn K. Glei

Keith Yamashita

Emily Heyward

Andy Dunn

william Allen

Rich Armstrong

Sean Blanda

Neil Blumenthal

Craig Dalton

Joel Gascoigne

Jane ni Dhulchaointigh

Tim O’Reilly

Miként tegyük termékünket egyúttal vonzó üggyé is? Miért előnyös a márkaépítés szempontjából, ha átláthatóvá tesszük a cégünket? Hogyan vonjuk be vevőinket a történetünkbe? Ebben az igényesen összeállított kötetben húsz, a maga területén meghatározó vezető, többek között Scott Belsky, Seth Godin és Simon Sinek mutatja be, hogyan kamatoztassuk kreativitásunkat az üzleti életben. Praktikus tippeket kapunk a vállalkozásunk céljának meghatározása, a termék(élmény)fejlesztés, az ügyfeleink szolgálata és a csapatvezetés témájában. Páratlan segítség, hogy valódi hatást gyakorolhassunk a számunkra legfontosabb területeken. A Behance azért hozta létre a 99U-t, hogy összeállítsa az ötletek megvalósítását segítő „hiányzó tananyagot”. Webby-díjas website-jukon, a 99U.com-on interjúkat, cikkeket és videókat tesznek közzé, évenként megrendezik New Yorkban a 99U Konferenciát, és ezt a témát járja körül korábbi bestsellerük, A megvalósítás – hogy az ötlet valóra váljon, valamint legújabb 99U könyvsorozatuk is. A Behance a kreatív projektek bemutatásának és megismerésének teret adó, vezető online platform. Küldetésének érzi a kreatív szakemberek támogatását. A legkülönfélébb ágazatok alkotói a portál révén szereplési lehetőséghez jutnak és hírnévre tehetnek szert. Mindezek mellett számtalan internetes oldal portfóliómegosztó felülete is a Behance megoldásaira épül, ilyen például az Adweek, a Rhode Island School of Design és a National Design Awards website-ja. Világszerte számos vállalat és rajongó használja a Behance-et, hogy figyelemmel kísérje vagy akár szerződtesse a legnagyobb tehetségeket.”

Az értékteremtő vállalkozás felépítése

Alkossunk maradandót!

Suzanna Becker

Klaus Obermayer

Proceedings of the 2002 Neural Information Processing Systems Conference. The annual Neural Information Processing (NIPS) meeting is the flagship conference on neural computation. The conference draws a diverse group of attendees--physicists, neuroscientists, mathematicians, statisticians, and computer scientists--and the presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, vision, speech and signal processing, reinforcement learning and control, implementations, and applications. Only about thirty percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. This volume contains all the papers presented at the 2002 conference.

Proceedings of the 2002 Conference

Advances in Neural Information Processing Systems 15

Lawrence K. Saul

Bernhard Schölkopf

Papers presented at the 2003 Neural Information Processing Conference by leading physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The annual Neural Information Processing (NIPS) conference is the flagship meeting on neural computation. It draws a diverse group of attendees -- physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, brain imaging, vision, speech and signal processing, reinforcement learning and control, emerging technologies, and applications. Only thirty percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. This volume contains all the papers presented at the 2003 conference.

Proceedings of the 2003 Conference

Advances in Neural Information Processing Systems 16

Dieter Fox

Ronald C. Arkin

Wolfram Burgard

Probablistic robotics is a growing area in the subject, concerned with perception and control in the face of uncertainty and giving robots a level of robustness in real-world situations. This book introduces techniques and algorithms in the field.

Probabilistic Robotics

Sebastian Thrun

About

Books

Join the club