Abstract
Deep Learning (DL) is a branch of machine learning based on multiple processing layers with complex structure, or otherwise composed of multiple non-linear transformations. Diverse DL models are used for solving different tasks, but have some common features and identic problems. Eight ideas for DL features organization and problems solving are outlined, the DL main goal is specified. The elements and structure of deep learning neuro informational model are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nielsen, M.: Neural Networks and Deep Learning, draft book in preparation (2016). http://neuralnetworksanddeeplearning.com
Rumelhart, D., Hinton, G., Williams, R.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)
Hecht-Nielsen, R.: Counterpropagation networks. Appl. Opt. 26(23), 4979–4984 (1987)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybern. 43(1), 59–69 (1982)
Karp, G.: Cell and Molecular Biology: Concepts and Experiments, 4th edn. Wiley, Hoboken (2005)
Broomhead, D., Lowe, D.: Multivariable functional interpolation and adaptive networks. Complex Syst. 2, 321–355 (1988)
Hecht-Nielsen, R.: Confabulation Theory. Springer, Heidelberg (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Smolin, V. (2016). Some Ideas of Informational Deep Neural Networks Structural Organization. In: Cheng, L., Liu, Q., Ronzhin, A. (eds) Advances in Neural Networks – ISNN 2016. ISNN 2016. Lecture Notes in Computer Science(), vol 9719. Springer, Cham. https://doi.org/10.1007/978-3-319-40663-3_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-40663-3_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-40662-6
Online ISBN: 978-3-319-40663-3
eBook Packages: Computer ScienceComputer Science (R0)