Search: onr:"swepub:oai:DiVA.org:kth-6236" >
Towards Cortex Size...
Towards Cortex Sized Artificial Neural Systems
-
- Johansson, Christopher (author)
- KTH,Numerisk Analys och Datalogi, NADA
-
- Lansner, Anders (author)
- KTH,Numerisk Analys och Datalogi, NADA
-
(creator_code:org_t)
- Elsevier BV, 2007
- 2007
- English.
-
In: Neural Networks. - : Elsevier BV. - 0893-6080 .- 1879-2782. ; 20:1, s. 48-61
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- 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.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- cerebral cortex
- neocortex
- attractor neural networks
- cortical model
- large scale implementation
- cluster computers
- hypercolumns
- fixed-point arithmetic
- Computer science
- Datalogi
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
To the university's database