An effective and novel roller bearing fault diagnosis technique based on empirical mode decomposition (EMD) energy entropy and support vector machine (SVM) is put forward in this article. The vibration signal of roller bearing is decomposed by EMD and the first 5 intrinsic mode function (IMF) components are obtained. SVM served as a fault diagnosis classifier and the extracted energy features of the first 5 IMFs are taken as network input vectors, and then the fault bearing and the normal bearing can be distinguished. An technique for fault of roller bearing by SVM is evaluated against a series of fault diagnosis methods that are widely used in machinery, with particular regard to the effect of training set size on fault diagnosis accuracy. We trained the SVM using RBF kernel function. We compare our experimental results with the existing results given by SMO and SVM-light algorithms. It can be seen that the fault diagnosis method based on SVM-light is superior to that based on SMO in diagnosis accuracy of roller bearing. In addition to the SVM, the same datasets were classified using RBF NN and Hopfield NN. The experimental results show that the technique of support vector machine based on EMD energy entropy has higher fault diagnosis ability.