Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.
%0 Book
%1 Bengio09
%A Bengio, Yoshua
%B Foundations and Trends in Machine Learning
%C Boston
%D 2009
%I Now
%K 01801 103 book numerical ai data pattern recognition analysis learn algorithm
%R 10.1561/2200000006
%T Learning Deep Architectures for AI
%X Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.
%@ 978-1-60198-294-0
@book{Bengio09,
abstract = {Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the state-of-the-art in certain areas. This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.},
added-at = {2018-02-10T18:29:44.000+0100},
address = {Boston},
author = {Bengio, Yoshua},
biburl = {https://www.bibsonomy.org/bibtex/2b2e006b758477b1b916d942ccb7be711/flint63},
doi = {10.1561/2200000006},
file = {Journal Issue:2009/Bengio09.pdf:PDF;Now Product page:https\://www.nowpublishers.com/article/Details/MAL-006:URL;Amazon Search inside:http\://www.amazon.de/gp/reader/1601982941/:URL},
groups = {public},
interhash = {30174ec5e2667a039cdc30c5d359dc47},
intrahash = {b2e006b758477b1b916d942ccb7be711},
isbn = {978-1-60198-294-0},
keywords = {01801 103 book numerical ai data pattern recognition analysis learn algorithm},
publisher = {Now},
series = {Foundations and Trends in Machine Learning},
timestamp = {2018-04-16T12:37:02.000+0200},
title = {Learning Deep Architectures for {AI}},
username = {flint63},
year = 2009
}