Robustness of Artificial Metaplasticity Learning to Erroneous Input Distribution Assumptions

Artificial Metaplasticity learning algorithm is inspired by the biological metaplasticity property of neurons and Shannon’s information theory. In this research, Artificial Metaplasticity on multilayer perceptron (AMMLP) is compared with regular Backpropagation by using input sets generated with different probability distributions: Gaussian, Exponential, Uniform and Rayleigh. Artificial Metaplasticity shows better results than regular Backpropagation for Gaussian and Uniform distribution while regular Backpropagation shows better results for Exponential and Rayleigh distributions.

[1]  Emilio Del-Moral-Hernandez,et al.  A Preliminary Neural Model for Movement Direction Recognition Based on Biologically Plausible Plasticity Rules , 2007, IWINAC.

[2]  José R. Álvarez,et al.  Nature Inspired Problem-Solving Methods in Knowledge Engineering, Second International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2007, La Manga del Mar Menor, Spain, June 18-21, 2007, Proceedings, Part II , 2007, IWINAC.

[3]  Diego Andina,et al.  Artificial Metaplasticity Neural Network Applied to Credit Scoring , 2011, Int. J. Neural Syst..

[4]  Luca Berdondini,et al.  Network Dynamics and Synchronous Activity in cultured Cortical Neurons , 2007, Int. J. Neural Syst..

[5]  Diego Andina,et al.  Breast Cancer Classification Applying Artificial Metaplasticity , 2009, IWINAC.

[6]  Wickliffe C. Abraham,et al.  Metaplasticity: Key Element in Memory and Learning? , 1999, News in physiological sciences : an international journal of physiology produced jointly by the International Union of Physiological Sciences and the American Physiological Society.

[7]  Diego Andina,et al.  Artificial Metaplasticity can Improve Artificial Neural Networks Learning , 2013, Intell. Autom. Soft Comput..

[8]  D. Andina,et al.  Wood defects classification using Artificial Metaplasticity neural network , 2009, 2009 35th Annual Conference of IEEE Industrial Electronics.

[9]  Joel Quintanilla-Domínguez,et al.  Breast cancer classification applying artificial metaplasticity algorithm , 2011, Neurocomputing.

[10]  M. Bear,et al.  LTP and LTD An Embarrassment of Riches , 2004, Neuron.

[11]  P. Jedlicka,et al.  Synaptic plasticity, metaplasticity and BCM theory. , 2002, Bratislavske lekarske listy.

[12]  M. Bear,et al.  Metaplasticity: the plasticity of synaptic plasticity , 1996, Trends in Neurosciences.