Learning Rate Optimization in CNN for Accurate Ophthalmic Classification
Mahmoud Smaida1, Serhii Yaroshchak2, Ahmed Y. Ben Sasi3
1Mahmoud Smaida*, Department of Computer, The National University of Water and Environmental Engineering, Revine, Ukraine.
2Serhii Yaroshchak, Applied Mathematics, The National University of Water and Environmental Engineering, Revine, Ukraine.
3Ahmed Y. Ben Sasi, Department of Computer, The College of Industrial Technology, Misurata, Libya.
Manuscript received on January 08, 2021. | Revised Manuscript received on January 15, 2021. | Manuscript published on February 28, 2021. | PP: 211-216 | Volume-10 Issue-4, February 2021 | Retrieval Number: 100.1/ijitee.B82591210220| DOI: 10.35940/ijitee.B8259.0210421
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: One of the most important hyper-parameters for model training and generalization is the learning rate. Recently, many research studies have shown that optimizing the learning rate schedule is very useful for training deep neural networks to get accurate and efficient results. In this paper, different learning rate schedules using some comprehensive optimization techniques have been compared in order to measure the accuracy of a convolutional neural network CNN model to classify four ophthalmic conditions. In this work, a deep learning CNN based on Keras and TensorFlow has been deployed using Python on a database that contains 1692 images, which consists of four types of ophthalmic cases: Glaucoma, Myopia, Diabetic retinopathy, and Normal eyes. The CNN model has been trained on Google Colab. GPU with different learning rate schedules and adaptive learning algorithms. Constant learning rate, time-based decay, step-based decay, exponential decay, and adaptive learning rate optimization techniques for deep learning have been addressed. Adam adaptive learning rate method. has outperformed the other optimization techniques and achieved the best model accuracy of 92.58% for training set and 80.49% for validation datasets, respectively.
Keywords: CNN model, Deep learning, Ophthalmic classification, Time-based decay, Step-based decay, Exponential decay, Adaptive learning rate.