Abstract
We investigate how structured information processing within a neural net can emerge as a result of unsupervised learning from data. The model consists of input neurons and hidden neurons which are re- currently connected. On the basis of a maximum likelihood framework the task is to reconstruct given input data using the code of the hid- den units. Hidden neurons are fully connected and they may code on different hierarchical levels. The hidden neurons are separated into two groups by their intrinsic parameters which control their firing properties. These differential properties encourage the two groups to code on two different hierarchical levels. We train the net using data which are either generated by two linear models acting in parallel or by a hierarchical process. As a result of training the net captures the structure of the data generation process. Simulations were performed with two different neu- ral network models, both trained to be maximum likelihood predictors of the training data. A (non-linear) hierarchical Kalman filter model and a Helmholtz machine. Here we compare both models to the neural cir- cuitry in the cortex. The results imply that the division of the cortex into laterally and hierarchically organized areas can evolve to a certain degree as an adaptation to the environment.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M. Abeles. Corticonics. Neural Cirquits of the Cerebral Cortex. Cambridge University Press, 1991.
Anthony J.Bell and Terrence J. Sejnowski. An information-maximization approach to blind separation and blind deconvolution. Neur. Comp., 7(6):1129–1159, 1995.
P. Dayan, G.E. Hinton, R. Neal, and R.S. Zemel. The Helmholtz machine. Neur. Comp., 7:1022–1037, 1995.
M.J. Donoghue and P. Rakic. Molecular evidence for the early specification of presumptive functional domains in the embryonic primate cerebral cortex. J. Neurosci., 19(14):5967–79, 1999.
D.J. Felleman and D.C. Van Essen. Distributed hierarchical processing in the primate cerebral cortex. Cerebral Cortex, 1:1–47, 1991.
S. Geyer, M. Matelli, G. Luppino, A. Schleicher, Y. Jansen, N. Palomero-Gallagher, and K. Zilles. Receptor autoradiographic mapping of the mesial motor and pre-motor cortex of the macaque monkey. J. Comp. Neurol., 397:231–250, 1998.
S. Haykin. Neural Networks. A Comprehensive Foundation. Macmillan College Publishing Company, 1994.
G.E. Hinton, P. Dayan, B.J. Frey, and R. Neal. The wake-sleep algorithm for unsupervised neural networks. Science, 268:1158–1161, 1995.
M. Kawato, H. Hayakawa, and T. Inui. A forward-inverse optics model of reciprocal connections between visual cortical areas. Network, 4:415–422, 1993.
B.A. Olshausen. Learning linear, sparse, factorial codes. A.I. Memo 1580, Massachusetts Institute of Technology., 1996.
R.P.N. Rao and D.H. Ballard. Dynamic model of visual recognition predicts neural response properties of the visual cortex. Neur. Comp., 9(4):721–763, 1997.
J.W. Scannell, C. Blakemore, and M.P. Young. Analysis of connectivity in the cat cerebral cortex. J. Neurosci., 15(2):1463–1483, 1995.
C. Weber and K. Obermayer.Emergence of modularity within one sheet of intrinsically active stochastic neurons. In Proceedings ICONIP, 2000.
C. Weber and K. Obermayer. Structured models from structured data: emergence of modular information processing within one sheet of neurons. In Proceedings IJCNN, 2000.
M.P. Young. The organization of neural systems in the primate cerebral cortex. Proc. R. Soc. Lond. B, 252:13–18, 1993.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Weber, C., Obermayer, K. (2001). Emergence of Modularity within One Sheet of Neurons: A Model Comparison. In: Wermter, S., Austin, J., Willshaw, D. (eds) Emergent Neural Computational Architectures Based on Neuroscience. Lecture Notes in Computer Science(), vol 2036. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44597-8_4
Download citation
DOI: https://doi.org/10.1007/3-540-44597-8_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42363-8
Online ISBN: 978-3-540-44597-5
eBook Packages: Springer Book Archive