Learning in linear neural networks: a survey
Baldi, P.F.
Hornik, K.
Div. of Biol., California Inst. of Technol., Pasadena, CA;
This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: Jul 1995
Volume: 6,
Issue: 4
On page(s): 837-858
ISSN: 1045-9227
References Cited: 52
CODEN: ITNNEP
INSPEC Accession Number: 5002611
Digital Object Identifier: 10.1109/72.392248
Current Version Published: 2002-08-06
Abstract
Networks of linear units are the simplest kind of networks, where
the basic questions related to learning, generalization, and
self-organization can sometimes be answered analytically. We survey most
of the known results on linear networks, including: 1) backpropagation
learning and the structure of the error function landscape, 2) the
temporal evolution of generalization, and 3) unsupervised learning
algorithms and their properties. The connections to classical
statistical ideas, such as principal component analysis (PCA), are
emphasized as well as several simple but challenging open questions. A
few new results are also spread across the paper, including an analysis
of the effect of noise on backpropagation networks and a unified view of
all unsupervised algorithms
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
