Towards Cortex Sized Artificial Neural Systems
2007 (English)In: Neural Networks, ISSN 0893-6080, E-ISSN 1879-2782, Vol. 20, no 1, 48-61 p.Article in journal (Refereed) Published
We propose, implement, and discuss an abstract model of the mammalian neocortex. This model is instantiated with a sparse recurrently connected neural network that has spiking leaky integrator units and continuous Hebbian learning. First we study the structure, modularization, and size of neocortex, and then we describe a generic computational model of the cortical circuitry. A characterizing feature of the model is that it is based on the modularization of neocortex into hypercolumns and minicolumns.Both a floating- and fixed-point arithmetic implementation of the model are presented along with simulation results. We conclude that an implementation on a cluster computer is not communication but computation bounded. A mouse and rat cortex sized version of our model executes in 44% and 23% of real-time respectively. Further, an instance of the model with 1.6 x 10(6) units and 2 x 10(11) connections performed noise reduction and pattern completion. These implementations represent the current frontier of large-scale abstract neural network simulations in terms of network size and running speed.
Place, publisher, year, edition, pages
2007. Vol. 20, no 1, 48-61 p.
cerebral cortex, neocortex, attractor neural networks, cortical model, large scale implementation, cluster computers, hypercolumns, fixed-point arithmetic
IdentifiersURN: urn:nbn:se:kth:diva-6236DOI: 10.1016/j.neunet.2006.05.029ISI: 000243841900004PubMedID: 16860539ScopusID: 2-s2.0-33845642736OAI: oai:DiVA.org:kth-6236DiVA: diva2:10888
QC 201009022006-10-092006-10-092011-12-27Bibliographically approved