Application of Artificial Metaplasticity fundamentals to WBCD Breast Cancer Database classification method

The Metaplasticity is an inherent property of the Biological neuron connections that consists in the capacity of modifying the learning mechanism using the information present in the network itself during the training. This concept can be applied to Artificial Learning Algorithms using a technique called Artificial Metaplasticity. The idea is to improve the results in Machine Learning taking as the base the hypothesis studied by Metaplasticity in Biological Learning. This paper presents and discuss the results of applying an Artificial Metaplasticity implementation based on the information present at the output of the network in Multilayer Perceptrons at artificial neuron learning level. The objective of this study is a state-of-the-art research: the diagnosis of breast cancer data from the Wisconsin Breast Cancer Database.