Welcome to the InfoSci Platform

Reference Hub

This research has been cited in:

Article
Fully Elman Neural Network: A Novel Deep Recurrent Neural Network Optimized by an Improved Harris Hawks Algorithm for Classification of Pulmonary Arterial Wedge PressureIEEE Transactions on Biomedical Engineering10.1109/TBME.2021.3129459
Article
Building segmentation from UAV orthomosaics using unet-resnet-34 optimised with grey wolf optimisation algorithmSmart Construction and Sustainable Cities10.1007/s44268-023-00019-x

Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks

Sajid Nazir, Shushma Patel, Dilip Patel

Source Title: International Journal of Artificial Intelligence and Machine Learning (IJAIML)10(2)

ISSN: 2642-1577|EISSN: 2642-1585|EISBN13: 9781799809289|DOI: 10.4018/IJAIML.2020070101

Cite Article Cite Article

MLA

Nazir, Sajid, et al. "Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks." IJAIML vol.10, no.2 2020: pp.1-17. http://doi.org/10.4018/IJAIML.2020070101

APA

Nazir, S., Patel, S., & Patel, D. (2020). Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks. International Journal of Artificial Intelligence and Machine Learning (IJAIML), 10(2), 1-17. http://doi.org/10.4018/IJAIML.2020070101

Chicago

Nazir, Sajid, Shushma Patel, and Dilip Patel. "Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks," International Journal of Artificial Intelligence and Machine Learning (IJAIML) 10, no.2: 1-17. http://doi.org/10.4018/IJAIML.2020070101

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

The increased processing power of graphical processing units (GPUs) and the availability of large image datasets has fostered a renewed interest in extracting semantic information from images. Promising results for complex image categorization problems have been achieved using deep learning, with neural networks comprised of many layers. Convolutional neural networks (CNN) are one such architecture which provides more opportunities for image classification. Advances in CNN enable the development of training models using large labelled image datasets, but the hyper parameters need to be specified, which is challenging and complex due to the large number of parameters. A substantial amount of computational power and processing time is required to determine the optimal hyper parameters to define a model yielding good results. This article provides a survey of the hyper parameter search and optimization methods for CNN architectures.