Learning to Learn
Sebastian Thrun, Lorien Pratt
Springer US, 1998 - Computers - 354 pages
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.
What people are saying - Write a review
Sebastian Thrun's Homepage
Learning to learn is an exciting new research direction within machine learning. Similar to traditional machine learning algorithms, the methods described ...
thrun.org/ papers/ thrun.book3.html
Post-NIPS*95 Workshop on Transfer in Inductive Systems
"Learning to Learn: Knowledge Consolidation .... Fundamental problems/issues in learning to learn ... Theoretical models of learning to learn ...
plato.acadiau.ca/ courses/ comp/ dsilver/ NIPS95_LTL/ transfer.workshop.1995.html
LEARNING TO LEARN, SELF-IMPROVEMENT, METALEARNING, META-LEARNING ...
LEARNING TO LEARN. METALEARNING MACHINES AND SELF-IMPROVEMENT ... In S. Thrun and L. Pratt, eds., Learning to learn, Kluwer, pages 293-309, 1997. ...
www.idsia.ch/ ~juergen/ metalearner.html
Learning to Learn Using Gradient Descent
appealing topics: “meta-learning” or “learning to learn” [4,14,13,11]. A meta- ..... Learning To Learn. Kluwer Academic Pub., 1997. 15. P. Utgoff. ...
www.springerlink.com/ index/ 6YVPAK8YUA4DGR6Q.pdf
Theoretical Models of Learning to Learn - Baxter (researchindex)
A Machine can only learn if it is biased in some way. Typically the bias is supplied by hand, for example through the choice of an appropriate set of ...
Empirical Bayes for Learning to Learn
studying learning to learn. In multitask learning we. are dealing with many related tasks. ...... model of learning to learn via multiple task sam- ...
www.snn.ru.nl/ reports/ Heskes.empirical.ps.gz
Learning to learn
Learning to learn: introduction and overview. Source, Learning to learn table of contents. Pages: 3 - 17. Year of Publication: 1998. ISBN:0-7923-8047-9 ...
Robotics Institute: Learning to Learn: Introduction and Overview
Learning To Learn, S. Thrun and L. Pratt, ed., Kluwer Academic Publishers, 1998. Jump to: Text Reference | bibtex Reference ...
www.ri.cmu.edu/ pubs/ pub_640.html
Using Meta-Learning to Support Data Mining
Within the learning-to-learn paradigm, a continuous learner can extract .... A field related to the idea of learning-to-learn is that of dynamic bias ...
www.tmrfindia.org/ ijcsa/ V1I13.pdf
[Paper] Mechanisms for Inductive Learning: From Base-learning to ...
KEY WORDS Inductive Learning, Meta-Learning, Bias Learning, Learning to Learn 1 Introduction Inductive methods represent the basis behind knowl- edge ...