Accessibility navigation


Towards optimizing the selection of neurons in affordable neural networks

Ausoni, J. T., Mitchell, R. and Holderbaum, W. (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.

[img] Text
· Restricted to Repository staff only
· The Copyright of this document has not been checked yet. This may affect its availability.

370kB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

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)
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
ID Code:36802
Uncontrolled Keywords:ANN, neuron selection, optimization, saliency, redundancy.

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation