Abstract
Biologically plausible artificial neural networks represent a promising novel approach in bio-inspired computational systems. In these systems, the models are based on existing knowledge of neurophysiological processing principles. Research in this field has increased in the last few years and has generated new viewpoints, propositions and models that are closer to the known features of the human brain. Some researchers have recently focused their studies on this innovative field in order to establish a consensus on what an artificial neural network is in the domain of biological realism. Domain specific synthetic data sets are generally used in the evaluation of those artificial neural networks because they simulate predictive tasks and potential problems caused by human intervention. This paper deals with the analysis of influence of the anomalies generated by human intervention in credit approval process. Such anomalies modify real classification, performance and accuracy. In this analysis, we evaluated a real data set that represents human actions over personal credit approval and fraud identification by using a biologically more plausible artificial neural network proposal.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barabási, A.L., Albert, R.: Emergence of scaling in random networks. Science 286, 509–512 (1999)
Crick, F.: The Recent Excitement about Neural Networks. Nature 337, 129–132 (1989)
Faceli, K., Lorena, A.C., Gama, J., Carvalho, A.C.P.L.F.: Artificial Intelligence - A machine learning approach. LTC Press (2011) (in Portuguese)
Gerstner, W., Kistler, W.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press (2002)
Hebb, D.: The Organization of Behavior. Cambridge-Wiley (1949)
Japkowicz, N., Shah, M.: Evaluating Learning Algorithms: A Classification Perspective. Cambridge University Press (2011)
Kandel, R., Schwartz, J.H., Jessell, T.M.: Essentials of Neural Science and Behavior. Appleton and Lange, Stamford, Connecticut (1995)
Kandel, R., Schwartz, J.H., Jessell, T.M.: Principles of Neural Science, 4th edn. McGraw-Hill (2000)
Knudsen, E.I.: Supervised Learning in the Brain. The Journal of Neuroscience 14(7), 3985–3997 (1994)
Maass, W.: Networks of spiking neurons: The third generation of neural network models. Neural Networks 10, 1659–1671 (1997)
Newman, D.J., Hettich, S., Blake, C.L., Merz, C.J.: Irvine, CA (1998), http://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits
O’Reilly, R.C.: Biologically plausible error-driven learning using local activation differences: The generalized recirculation algorithm. Neural Computation, 895–938 (1996)
O’Reilly, R.C.: Six principles for biologically-based computational models for cortical cognition. Trends in Cognitive Science 2, 455–462 (1998)
O’Reilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience - Understanding the Mind by Simulating the Brain. The MIT Press (2000)
Rosa, J.L.G.: An artificial neural network model based on neuroscience: Looking closely at the brain. In: Kurková, R.N.V., Steele, N.C., Kárný, M. (eds.) Artificial Neural Nets and Genetic Algorithms - Proc. Intl. Conf. in Prague, Czech Republic, pp. 138–141. Springer (2001)
Ruf, B., Schmitt, M.: Self-Organization of Spiking Neurons Using Action Potential Timing. IEEE Transactions on Neural Network 9(3) (1998)
Silva, A.B., Rosa, J.L.G.: Biological Plausibility in Artificial Neural Networks: An Improvement on Earlier Models. In: Proc. The 7th. International Conference on Machine Learning and Applications, ICMLA 2008, San Diego, California, USA, December 11-13, IEEE Computer Society Press (2008)
Silva, A.B., Rosa, J.L.G.: Advances on Criteria for Biological Plausibility in Artificial Neural Networks: Think of Learning Processes. In: Proc. The 2011 International Joint Conference on Neural Networks, IJCNN 2011, San Jose, California, USA, July 31-August 5, pp. 1394–1401. IEEE Computer Society Press (2011) ISBN: 978-1-4244-9636-5
Song, S., Miller, K.D., Abbott, L.F.: Competitive hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience 3(9), 919–926 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
da Silva, A.B., Rosa, J.L.G. (2013). Biological Plausibility in an Artificial Neural Network Applied to Real Predictive Tasks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2013. Lecture Notes in Computer Science(), vol 7894. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38658-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-38658-9_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38657-2
Online ISBN: 978-3-642-38658-9
eBook Packages: Computer ScienceComputer Science (R0)