Abstract

Learning rates in gradient descent algorithms have significant effects especially on the accuracy of a Capsule Neural Network (CNN). Choosing an appropriate learning rate is still an issue to date. Many developers still have a problem in selecting a learning rate for CNN leading to low accuracies in classification. This gap motivated this study to assess the effect of learning rate on the accuracy of a developed (CNN). There are no predefined learning rates in CNN and therefore it is hard for researchers to know what learning rate will give good results. This work, therefore, focused on assessing the effect of learning rate on the accuracy of a CNN by using different learning rates and observing the best performance. The contribution of this work is to give an appropriate learning rate for CNNs to improve accuracy during classification. This work has assessed the effect of different learning rates and came up with the most appropriate learning rate for CNN plant leaf disease classification. Part of the images used in this work was from the PlantVillage dataset while others were from the Nepal database. The images were pre-processed then subjected to the original CNN model for classification. When the learning rate was 0.0001, the best performance was 99.4% on testing and 100% on training. When the learning rate was 0.00001, the highest performance was 97% on testing and 99.9% on training. The lowest performance observed was 81% accuracy on testing and 99% on training when the learning rate was 0.001. This work observed that CNN was able to achieve the highest accuracy with a learning rate of 0.0001. The best Convolutional Neural Network accuracy observed was 98% on testing and 100% on training when the learning rate was 0.0001.

Highlights

  • Deep learning has been used over time for plant leaf disease detection and classification

  • In the third and fourth experiments, the highest accuracy reached on training was 94% while the testing accuracy was 97.0% for the capsule neural network (CNN) while the Convolutional neural network (ConvNet) had 97% accuracy on testing and 99% accuracy on training

  • In the seventh and eighth experiments, the accuracy observed on training was 99.9% while that of testing was 99% for Capsule neural network (CNN) while the training and testing accuracy for the convolutional neural network (ConvNet) was 100% and 96.2%, respectively

Read more

Summary

INTRODUCTION

Deep learning has been used over time for plant leaf disease detection and classification. The process of training a neural network using an algorithm, for example, the error back-propagation [1, 2, 3, 4] is normally time-consuming, especially when working on complex problems These types of algorithms naturally have a learning rate parameter that controls the extents by which the weights can change based on an observed error that was noted on the training set. This paper aims to investigate the effect of learning rate on the accuracy of CNN's as applied in plant disease detection. A total of 24 experiments were conducted for plant leaf disease classification using the three learning rates and 0.0001 gave the best classification results of 99.4% accuracy on testing and 100% on training

RELATED WORK
Learning Rate
The Number of Layers that are Hidden
Momentum
Activation Function
Mini-batch Size
Epochs
PROPOSED WORK METHODOLOGY
The Data
Image Acquisition
Pre-processing
Training and Testing Data Sets
Experimental Results
DISCUSSION
VIII. CONCLUSION
Findings
Cambridge

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.