Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)

The importance of character recognition cannot be overemphasized. It finds applications in many automated systems. In most cases, these applications require high precision (e.g. automatic grading system, document digitization, license plate recognition systems, e.t.c) as well as low resource overhead. However, these are conflicting requirements, because the more the precision required, the more computation needed hence the more increase in resource overhead. In the research, two classification algorithms in Artificial Neural Networks (ANN): Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) were applied to hand-written digit recognition and their performance is investigated. The duo was compared in terms of resources required for training and accuracy. It is found that MLP-NN is much faster to train (5.5min) compared to RBF (50.0min). However, during testing, it is found that both have an accuracy of ≈ 95%.