Lists
Lists![[thumbnail of Ausonio_Mitchell_Holderbaum.pdf]](https://reading-clone.eprints-hosting.org/style/images/fileicons/text.png "Ausonio_Mitchell_Holderbaum.pdf")
Ausoni, J. T., Mitchell, R. and Holderbaum, W. 
ORCID: https://orcid.org/0000-0002-1677-9624
(2014)
Towards optimizing the selection of neurons in affordable neural networks.
In: The 2014 International Conference on Artificial Intelligence, July 21-24, 2014,, Las Vegas, Nevada, USA.
Abstract/Summary
This paper considers variations of a neuron pool selection method known as Affordable Neural Network (AfNN). A saliency measure, based on the second derivative of the objective function is proposed to assess the ability of a trained AfNN to provide neuronal redundancy. The discrepancies between the various affordability variants are explained by correlating unique sub group selections with relevant saliency variations. Overall this study shows that the method in which neurons are selected from a pool is more relevant to how salient individual neurons are, than how often a particular neuron is used during training. The findings herein are relevant to not only providing an analogy to brain function but, also, in optimizing the way a neural network using the affordability method is trained.
| Item Type | Conference or Workshop Item (Paper) |
| URI | https://reading-clone.eprints-hosting.org/id/eprint/36802 |
| Item Type | Conference or Workshop Item |
| Refereed | Yes |
| Divisions | Life Sciences > School of Biological Sciences > Department of Bio-Engineering Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science |
| Uncontrolled Keywords | ANN, neuron selection, optimization, saliency, redundancy. |
| Download/View statistics | View download statistics for this item |
University Staff: Request a correction | Centaur Editors: Update this record
