Cover of Learning to Learn
Read Time: ~5.9 hr

Learning to Learn

by Sebastian Thrun, Lorien Pratt (1998)

About this book

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.

Setting / LocationGlobal
Story EraModern Era
Protagonist / CoreLearning to Learn Lead Character

Readers who enjoyed this also loved

Cover of Algorithmic learning theory

Algorithmic learning theory

Ming Li, Akira Maruoka (eds

This book constitutes the refereed proceedings of the 8th International Workshop on Algorithmic Learning Theory, ALT'97, held in Sendai, Japan, in October 1997. The volume presents 26 revised full papers selected from 42 submissions. Also included are three invited papers by leading researchers. Among the topics addressed are PAC learning, learning algorithms, inductive learning, inductive inference, learning from examples, game-theoretical aspects, decision procedures, language learning, neural algorithms, and various other aspects of computational learning theory.

Cover of Artificial evolution

Artificial evolution

Cyril Fonlupt... [et al.], (eds

The Arti?cial Evolution conference was originally conceived as a forum for the French-speaking Evolutionary Computation community, but has of late been acquiring an European audience, with several papers from Germany, Austria, Italy, Spain... However, AE remains as intended a small and friendly gathering, which will continue to be held every two years. Previous AE meets were held in Toulouse, Brest, and Nˆ ?mes. This year, the hosting was done by the LIL (Laboratoire d’Informatique du Littoral) in the not-so-cold city of Dunkerque. The invited talk on “Fitness Landscapes and Evolutionary Algorithms” was delivered by Colin Reeves of Coventry University This volume contains a selection of the papers presented at the conference. Twenty-seven papers were presented orally at the conference, selected from over 40 papers refereed by the program committee. After the conference, each p- sentation was reviewed and 20 papers were retained and revised for publication in this volume. The papers in this volume have been grouped into the following ?ve sections which more or less re?ect the organization of the oral presentations. 1. Invited Paper: C. Reeves brightly describes the state of the art in Fitness Landscapes.

Cover of Programming in Prolog

Programming in Prolog

William F. Clocksin, Christopher S. Mellish

Since the first edition of this book in 1981, Prolog has continued to attract an unexpectedly great deal of interest in the computer science community and has turned out to be a basis for an important new family of programming languages and systems for Artificial Intelligence. In the preceding three editions, the authors have steadily added new material, improved the presentation, and corrected various minor errors to provide a textbook as well as a reference work for everyone who wants to study and use Prolog as a practical programming language. The authors concentrate on teaching "core" Prolog. All examples conform to this standard and will run on the most widely-used Prolog implementations some of which are listed in the appendices with indications as to how they diverge from the standard.

Cover of Deformable Avatars

Deformable Avatars

Nadia Magnenat-Thalmann, Daniel Thalmann

With the increasing success of Networked Virtual Environments, Games and Web 3D, there is a need for new techniques to permit the creation and animation of Virtual Humans. Users may be represented by realistic avatars that they can control, but also autonomous Virtual Humans agents can now inhabit these Virtual Worlds. Virtual Humans with their soft tissues, skin, muscles, organs and clothes are completely deformable. There are many methods to enable the representation and deformation of these structures. These methods may be geometric or physics-based. Presenting a selection of the latest research work addressing various aspects related to deformable avatars, this book covers complementary topics such as body modelling and animation, face modelling and animation, physics-based and free-form deformations, motion capture, avatars technologies and agents. This volume is comprised of the combined proceedings of the DEFORM'2000 and AVATARS'2000 workshops, which were sponsored by the International Federation for Information Processing (IFIP) and organized by IFIP Working Group 5.10. The workshops were held in Geneva and Lausanne, Switzerland in November/December 2000.

Learning to Learn by Sebastian Thrun, Lorien Pratt | Literally Just Books