Deep Learning Algorithms for Predicting Breast Cancer Based on Tumor Cells

This paper is the comparison of classification algorithms for breast cancer based on tumor cell. We focus on using deep learning algorithms to classify types of breast cancer with several of activation function: Tanh, Rectifier, Maxout and Exprectifier. And comparison with different machine learning methonds such as, Naïve Bayes(NB), Decision tree(DT), Support Vector Machine(SVM), Vote (DT+NB+SVM), Random Forest(RF) and AdaBoost. Experimental data were downloaded from breast cancer Wisconsin dataset and using machine learning tool rapidminer. Using ten-fold cross-validation. We found that the high accuracy of 96.99% with deep learning by Exprectifier activation function.