Towards optimizing the selection of neurons in affordable neural networks

Download

[thumbnail of Ausonio_Mitchell_Holderbaum.pdf]

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

Restricted to Repository staff only

Advice

Please see our End User Agreement.

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

Tools

Lists

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
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

Related URLs

Deposit Details

Date Deposited:	18 Jun 2014 15:13	Date item deposited into CentAUR
Last Modified:	23 Jul 2024 15:16	Date item last modified

References

[1] M. Clergue and P. Collard, “Genetic algorithm for artificial neurogenesis,” in Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on, 1998, pp. 410–415. [2] M. Mulligan, L. Lu, R. Overall, G. Kempermann, G. Rogers, M. Langston, and R. Williams, “Genetic analysis of bdnf expression cliques and adult neurogenesis in the hippocampus,” in Biomedical Sciences and Engineering Conference (BSEC), 2010, 2010, pp. 1–4. [3] O. Michel and P. Collard, “Artificial neurogenesis: an application to autonomous robotics,” in Tools with Artificial Intelligence, 1996., Proceedings Eighth IEEE International Conference on, 1996, pp. 207– 214. [4] R. P. Stroemer, T. A. Kent, and C. E. Hulsebosch, “Neocortical neural sprouting, synaptogenesis, and behavioral recovery after neocortical infarction in rats,” Stroke, vol. 26, no. 11, pp. 2135–2144, 1995. [Online]. Available: http://stroke.ahajournals.org/content/26/11/2135.abstract [5] Y. Uwate and Y. Nishio, “Back propagation learning of neural networks with chaotically-selected affordable neurons,” in Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on, may 2005, pp. 1481 – 1484 Vol. 2. [6] Y. Uwate, Y. Nishio, and R. Stoop, “Scale-rule selection of affordable neural network for chaotic time series learning,” in Circuit Theory and Design, 2007. ECCTD 2007. 18th European Conference on, 2007, pp. 811–814. [7] Y. Uwate and Y. Nishio, “Learning process of affordable neural network for backpropagation algorithm,” in Neural Networks (IJCNN), The 2010 International Joint Conference on, 2010, pp. 1–7. [8] L. Cun, Denker, and Solla, “Optimal brain damage,” AT&T Bell Laboratories, 1990. [Online]. Available: http://www.cnbc.cmu.edu/ plaut/IntroPDP/papers/ [9] R. Rivera and B. Dawes, “Boost c++ libraries,” 2014. [Online]. Available: http://www.boost.org [10] K. Bache and M. Lichman, “UCI machine learning repository,” 2013. [Online]. Available: http://archive.ics.uci.edu/ml

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

Search Google Scholar