Abstract
Several guiding principles for thought processes are proposed and a neural-network-type model implementing these principles is presented and studied. We suggest to consider thinking within an associative network built-up of overlapping memory states. We consider a homogeneous associative network as biological considerations rule out distinct conjunction units between the information (the memories) stored in the brain. We therefore propose that memory states have a dual functionality: They represent on one side the stored information and serve, on the other side, as the associative links in between the different dynamical states of the network which consists of transient attractors.
We implement these principles within a generalized winners-take-all neural network with sparse coding and an additional coupling to local reservoirs. We show that this network is capable to generate autonomously a self-sustained time-series of memory states which we identify with a thought process. Each memory state is associatively connected with its predecessor.
This system shows several emerging features, it is able (a) to recognize external patterns in a noisy background, (b) to focus attention autonomously and (c) to represent hierarchical memory states with an internal structure.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
Dorogovtsev, S.N., Mendes, J.F.F.: Evolution of Networks. Oxford University Press, Oxford (2003)
Hubel, D., Wiesel, T.: Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) in the cat. J. Neurophysiol. 28, 229–289 (1965)
McLeod, P., Plunkett, K., Rolls, E.T.: Introduction to connectionist modelling of cognitive processes. Oxford University Press, Oxford (1998)
Müller, B., Reinhardt, J., Strickland, M.T.: Neural Networks, An Introduction. Springer, Heidelberg (1995)
Fukai, T., Tanaka, S.: A simple neural network exhibiting selective activation of neuronal ensembles: from winner-take-all to winners-share-all. Neural Comp. 9, 77–97 (1997)
O’Reilly, R.C.: Six principles for biologically based computational models of cortical cognition. Trends Cog. Sci. 2, 455–462 (1998)
Kwon, T.M., Zervakis, M.: KWTA networks and their application. Multidim. Syst. and Sig. Proccessing 6, 333–346 (1995)
Riesenhuber, M., Poggio, T.: Are cortical models really bound by the “Binding Problem? Neuron 24, 87–93 (1999)
Mel, B., Fiser, J.: Minimizing Binding Errors Using Learned Conjunctive Features. Neural Comp. 12, 731–762 (2000)
Buhmann, J., Divko, R., Schulten, K.: Associative memory with high information content. Phys. Rev. A 39, 2689–2692 (1989)
Schuster, H.G.: Complex Adaptive Systems: An Introduction. Scator (2001)
Reynolds, J.H., Desimone, R.: The role of neural mechanisms of attention to solve the binding problem. Neuron 24, 19–29 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gros, C. (2005). Self-sustained Thought Processes in a Dense Associative Network. In: Furbach, U. (eds) KI 2005: Advances in Artificial Intelligence. KI 2005. Lecture Notes in Computer Science(), vol 3698. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11551263_29
Download citation
DOI: https://doi.org/10.1007/11551263_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28761-2
Online ISBN: 978-3-540-31818-7
eBook Packages: Computer ScienceComputer Science (R0)