Skip to main content

Hierarchical Network Models for Memory and Learning

  • Reference work entry
  • 238 Accesses


Deep hierarchical networks; Hubel–Wiesel models


Hierarchical models for learning and memory make use of a network of modules for solving a cognitive task such as object recognition. The modules are constructed with multiple child nodes being connected hierarchically to a parent node. The modules at the lower levels process and represent simpler features of an object, while the modules at the higher levels represent more complex features. Hierarchical models of learning are generally considered to be more biologically inspired than other learning methods such as feed forward neural networks because of (1) the number of layers of the architecture and (2) their ability to process and integrate information from simple to complex, thereby implicitly learning the underlying characteristics of the data.

Theoretical Background

Understanding how the visual cortex learns to recognize objects is a critical issue in both Neuroscience and artificial intelligence. As humans...

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
USD   3,400.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD   2,999.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions


  • Fukushima, K. (1980). Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, 36(4), 93–202.

    CrossRef  Google Scholar 

  • George, D., & Hawkins, J. (2009). Towards a mathematical theory of cortical microcircuits. PLoS Computational Biology, 5(10), e1000532. doi:10.1371/journal.pcbi.1000532.

    CrossRef  Google Scholar 

  • Goldstein, B. E. (2008). Sensation and perception (8th ed.). Belmont: Wadsworth.

    Google Scholar 

  • Hubel, D., & Wiesel, T. (1965). Receptive fields and functional architecture in two non striate visual areas (18 and 19) of a cat. Journal of Neurophysiology, 28, 229–289.

    Google Scholar 

  • Mountcastle, V. (1957). Modularity and topographic properties of single neurons of cat’s somatic sensory cortex. Journal of Neurophysiology, 20(4), 408–434.

    Google Scholar 

  • Reisenhuber, M., & Poggio, T. (1999). Hierarchical models of object recognition in cortex. Nature Neuroscience, 2(11), 1019–1025.

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Kiruthika Ramanathan .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer Science+Business Media, LLC

About this entry

Cite this entry

Ramanathan, K., Luping, S., Jianming, L., Chong, C.T. (2012). Hierarchical Network Models for Memory and Learning. In: Seel, N.M. (eds) Encyclopedia of the Sciences of Learning. Springer, Boston, MA.

Download citation