TechRxiv
Research_Report (PDF).pdf (609.96 kB)

Optimizing Convolutional Neural Network Parameters for Better Image Classification

Download (609.96 kB)
preprint
posted on 07.04.2020, 18:13 by Manik Dhingra, Sarthak Rawat, Jinan Fiaidhi
The work presented here works on getting higher performances for image recognition task using convolutional neural networks on the MNIST handwritten digits data-set. A range of techniques are compared for improvements with respect to time and accuracy, such as using one-shot Extreme Learning Machines (ELM) in place of the iteratively tuned fully-connected networks for classification, using transfer learning for faster convergence of image classification, and improving the size of data-set and making robust models by image augmentation. The final implementation is hosted on cloud as a web-service for better visualization of the prediction results.

History

Email Address of Submitting Author

mdhingra@lakeheadu.ca

Submitting Author's Institution

Lakehead University

Submitting Author's Country

Canada

Licence

Exports