Assessing the Efficacy of Logistic Regression, Multilayer Perceptron, and Convolutional Neural Network for Handwritten Digit Recognition

Abstract

The efficiency of handwritten digit recognition models greatly relies on the classification technique used and the optimization technique involved. Motivated to explore the efficacy of machine learning for handwritten digit recognition, this study assesses the performance of three machine learning techniques, logistic regression, multilayer perceptron, and convolutional neural network for recognition of handwritten digits. The experimental results reveal that convolutional neural network outperforms logistic regression and multilayer perceptron in terms of accuracy. However, convolutional neural network is quite expensive in terms of training time. Hence, it is concluded that there exists a tradeoff between accuracy and computational complexity of the applied machine learning techniques. This study also evaluates the performance of three optimizers namely, stochastic gradient descent, adadelta, and adam for handwritten digit recognition. The experiments conducted in the study demonstrate that adam performs better than stochastic gradient descent and adadelta.