Computational model of neocortical learning process: Prototype


Lee Seldon, Henry and Jing, Xian Teo (2014) Computational model of neocortical learning process: Prototype. In: Neural Information Processing. Lecture Notes in Computer Science (8834). Springer International Publishing, pp. 95-102. ISBN 978-3-319-12636-4

[img] Text
Computational model of neocortical learning process Prototype.pdf
Restricted to Repository staff only

Download (1MB)


The balloon model of neocortical growth and learning claims that learning starts with larger groups of functional units (neuron columns) responding to a signal, but with training and lateral cortical expansion and inhibition, the number of units responding to a particular signal decreases as the units become better able to differentiate similar inputs. This process is different from most Artificial Neural Networks, but has some similarities with Temporal Organizing Maps (TOM). This paper describes the architecture and testing of a prototype computational model, a variation on TOMs, which seeks to emulate the anatomical and physiological behavior. Preliminary results indicate that it is consistent with predictions.

Item Type: Book Section
Additional Information: Book Subtitle: 21st International Conference, ICONIP 2014, Kuching, Malaysia, November 3-6, 2014. Proceedings, Part I
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 12 Feb 2015 05:28
Last Modified: 12 Feb 2015 05:28


Downloads per month over past year

View ItemEdit (login required)