Convolutional Neural Network Hyper-Parameters Optimization based on Genetic Algorithms
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 10
Abstract
In machine learning for computer vision based applications, Convolutional Neural Network (CNN) is the most widely used technique for image classification. Despite these deep neural networks efficiency, choosing their optimal architecture for a given task remains an open problem. In fact, CNNs performance depends on many hyper-parameters namely CNN depth, convolutional layer number, filters number and their respective sizes. Many CNN structures have been manually designed by researchers and then evaluated to verify their efficiency. In this paper, our contribution is to propose an innovative approach, labeled Enhanced Elite CNN Model Propagation (Enhanced E-CNN-MP), to automatically learn the optimal structure of a CNN. To traverse the large search space of candidate solutions our approach is based on Genetic Algorithms (GA). These meta-heuristic algorithms are well-known for non-deterministic problem resolution. Simulations demonstrate the ability of the designed approach to compute optimal CNN hyper-parameters in a given classification task. Classification accuracy of the designed CNN based on Enhanced E-CNN-MP method, exceed that of public CNN even with the use of the Transfer Learning technique. Our contribution advances the current state by offering to scientists, regardless of their field of research, the ability of designing optimal CNNs for any particular classification problem.
Authors and Affiliations
Sehla Loussaief, Afef Abdelkrim
Keywords
Related Articles
- EP ID EP407519
- DOI 10.14569/IJACSA.2018.091031
- Views 114
- Downloads 0
Spectrum Sharing Security and Attacks in CRNs: a Review
Cognitive Radio plays a major part in communication technology by resolving the shortage of the spectrum through usage of dynamic spectrum access and artificial intelligence characteristics. The element of spectrum shari...
Classification of Melanoma Skin Cancer using Convolutional Neural Network
Melanoma cancer is a type of skin cancer and is the most dangerous one because it causes the most of skin cancer deaths. Melanoma comes from melanocyte cells, melanin-producing cells, so that melanomas are generally brow...
Low-Cost and Portable Ground Station for the Reception of NOAA Satellite Images
Currently, in Peru, the study of satellite images is increasing because it has the Earth observation satellite PeruSat-1. However, the cost of implementing a ground station is very high; for this reason, it is baffling t...
A New Viewpoint for Mining Frequent Patterns
According to the traditional viewpoint of Data mining, transactions are accumulated over a long period of time (in years) in order to find out the frequent patterns associated with a given threshold of support, and then...
Hybrid Texture based Classification of Breast Mammograms using Adaboost Classifier
Breast cancer is one of the most dangerous, leading and widespread cancers in the world especially in women. For breast analysis, digital mammography is the most suitable tool used to take mammograms for detection of can...