A comparative study between convolution neural networks and multi-layer perceptron networks for hand-written digits recognition
No Thumbnail Available
Rababaah, Aaron Rasheed
This paper presents an investigation that aims at comparing deep learning (DL) and traditional artificial neural networks (ANNs) in the application of hand-written digits recognition (HDR). In our study, convolution neural networks (CNNs) are a representative model for the DL models and the multi-layer perceptron (MLP) is a representative model for ANN models. The two models MLP and CNN were implemented using MATLAB development environment and tested using a publicly available image database. The databse consists of over 20,000 samples with all ten hand-written digits each of which is 24 × 24 pixels. The experimental results showed that the CNN model was superior to the MLP model with an average classification accuracy of 95.14% and 89.74% respectively. Furthermore, the CNN model was observed to have better performance stability and better execution efficiency as the MLP model requires human intervention to handcraft and pre-process the features of the digit patterns.