By Sebastian Thrun

Lifelong studying addresses events within which a learner faces a chain of alternative studying initiatives supplying the chance for synergy between them. Explanation-based neural community studying (EBNN) is a computer studying set of rules that transfers wisdom throughout a number of studying initiatives. while confronted with a brand new studying activity, EBNN exploits area wisdom gathered in past studying projects to consultant generalization within the new one. accordingly, EBNN generalizes extra thoroughly from much less info than related tools. Explanation-Based Neural community studying: A Lifelong Learning Approach describes the fundamental EBNN paradigm and investigates it within the context of supervised studying, reinforcement studying, robotics, and chess.
`The paradigm of lifelong studying - utilizing previous discovered wisdom to enhance next studying - is a promising path for a brand new iteration of computer studying algorithms. Given the necessity for extra actual studying equipment, it really is tricky to visualize a destiny for desktop studying that doesn't comprise this paradigm.'
From the Foreword via Tom M. Mitchell.

Show description

Read or Download Explanation-Based Neural Network Learning: A Lifelong Learning Approach (The Springer International Series in Engineering and Computer Science) PDF

Similar Artificial Intelligence books

Neural Network Systems Techniques and Applications, Fuzzy Logic and Expert Systems Applications, Volume 6

This quantity covers the combination of fuzzy common sense and professional structures. an important source within the box, it comprises ideas for utilising fuzzy structures to neural networks for modeling and keep watch over, systematic layout techniques for figuring out fuzzy neural platforms, suggestions for the layout of rule-based professional platforms utilizing the hugely parallel processing services of neural networks, the transformation of neural structures into rule-based professional platforms, the features and relative advantages of integrating fuzzy units, neural networks, genetic algorithms, and tough units, and purposes to approach identity and regulate in addition to nonparametric, nonlinear estimation.

Neural Networks and Intellect: Using Model-Based Concepts

Neural Networks and mind: utilizing Model-Based strategies describes a brand new mathematical idea of modeling box conception and its purposes to quite a few difficulties. interpreting the relationships between arithmetic, computations in neural networks, indicators and emblems in semiotics, and ideas of brain in psychology and philosophy, this specific textual content discusses deep philosophical questions intimately and relates them to arithmetic and the engineering of intelligence.

The MIT Guide to Science and Engineering Communication: Second Edition

This consultant covers the fundamentals of medical and engineering conversation, together with defining an viewers, operating with collaborators, looking the literature, organizing and drafting records, constructing photos, and documenting resources. The files coated contain memos, letters, proposals, growth stories, different kinds of experiences, magazine articles, oral displays, directions, and CVs and resumes.

Computational Logic and Human Thinking: How to Be Artificially Intelligent

The sensible advantages of computational good judgment don't need to be restricted to arithmetic and computing. As this e-book exhibits, traditional humans of their daily lives can benefit from the hot advances which have been built for synthetic intelligence. The ebook attracts upon comparable advancements in quite a few fields from philosophy to psychology and legislations.

Extra resources for Explanation-Based Neural Network Learning: A Lifelong Learning Approach (The Springer International Series in Engineering and Computer Science)

Show sample text content

Rated 4.77 of 5 – based on 37 votes