Handwritten Digit Recognition: Hyperparameters-Based Analysis
Open Access
- 29 August 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (17) , 5988
Abstract
Neural networks have several useful applications in machine learning. However, benefiting from the neural-network architecture can be tricky in some instances due to the large number of parameters that can influence performance. In general, given a particular dataset, a data scientist cannot do much to improve the efficiency of the model. However, by tuning certain hyperparameters, the model’s accuracy and time of execution can be improved. Hence, it is of utmost importance to select the optimal values of hyperparameters. Choosing the optimal values of hyperparameters requires experience and mastery of the machine learning paradigm. In this paper, neural network-based architectures are tested based on altering the values of hyperparameters for handwritten-based digit recognition. Various neural network-based models are used to analyze different aspects of the same, primarily accuracy based on hyperparameter values. The extensive experimentation setup in this article should, therefore, provide the most accurate and time-efficient solution models. Such an evaluation will help in selecting the optimized values of hyperparameters for similar tasks.Keywords
Funding Information
- Qassim University (COC-2020Y)
This publication has 19 references indexed in Scilit:
- A New Transfer Learning Algorithm in Semi-Supervised SettingIEEE Access, 2019
- Improving CNN-RNN Hybrid Networks for Handwriting Recognition2018
- Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN2018
- Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity dataJournal of Cheminformatics, 2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- A novel hybrid CNN–SVM classifier for recognizing handwritten digitsPattern Recognition, 2012
- Improved method of handwritten digit recognition tested on MNIST databaseImage and Vision Computing, 2004
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989
- Learning State Space Trajectories in Recurrent Neural NetworksNeural Computation, 1989
- Neocognitron: A neural network model for a mechanism of visual pattern recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1983