Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks
- Resource Type
- Authors
- Dilip Patel; Shushma Patel; Sajid Nazir
- Source
- International Journal of Artificial Intelligence and Machine Learning. 10:1-17
- Subject
- Hyperparameter
050210 logistics & transportation
Speedup
Artificial neural network
Contextual image classification
business.industry
Computer science
General Chemical Engineering
Deep learning
05 social sciences
Cognitive neuroscience of visual object recognition
Pattern recognition
02 engineering and technology
Convolutional neural network
Image (mathematics)
0502 economics and business
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
business
- Language
- ISSN
- 2642-1585
2642-1577
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.