Fast Automatic Optimisation of CNN Architectures for Image Classification Using Genetic Algorithm

Bakhshi, Ali; Noman, Nasimul; Chen, Zhiyong; Zamani, Mohsen; Chalup, Stephan K.

doi:10.1109/cec.2019.8790197

Cited by 29 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…GAs have been successfully used for NAS in image processing [9,11,20]. By encoding the network architecture as a chromosome or individual, GA methods strive to optimize the weights of the DNN architecture and/or the connections and hyperparameters of the DNN architecture.…”

Section: Related Workmentioning

confidence: 99%

“…2) Supportive combination: In this stream of work, GAs are used to optimize the connections and hyperparameters of the DNN architecture, while the weights are optimized using other algorithms such as the back-propagation [24]. FFNN optimization is proposed in [25], CNN optimization in [10,20,26,27] and RNN optimization in [26,28]. Mostly considered hyperparameters are the number of hidden layers, learning rate, type of optimizer, number of filters, layers' positions, and activation functions.…”

Section: Related Workmentioning

confidence: 99%

“…We can distinguish a few different research approaches within this stream. First, considering the network depth, we can separate them into two categories: fixed [10,27] and variable [20,26,28] network depth approaches. While the former might waste computational power in cases when the network depth is set to a value higher than optimal, the latter tries to find the optimal network depth and, thus, provides more computationally efficient candidate solutions.…”

Section: Related Workmentioning

confidence: 99%

“…The scalarization method is very sensitive to the weighting of the objectives and may require a large number of iterations in order to converge to a small part of the Pareto optimal front. Third, considering the way of DNN architectures building, we can separate them into two categories: layer stacking [9,20] and block stacking [11] approaches. The layer stacking approach is not preferred for complex classification problems, as it requires a deeper network vulnerable to the vanishing gradient problem where gradients become vanishingly small, preventing network training [5,6].…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification

Perenda¹,

Rajendran²,

Bovet³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automatic Modulation Classification (AMC) receives significant interest in the context of current and future wireless communication systems. Deep learning emerged as a powerful AMC tool, as it allows for the joint learning of discriminative features, and signal classification. However, the optimization of Deep Neural Network (DNN) architectures for AMC is a manual and time-consuming process that requires profound domain knowledge and much effort. Moreover, most proposed solutions focus mainly on classification accuracy, while optimization of network complexity is neglected. In this paper, we propose a novel bi-objective memetic algorithm, BO-NSMA, to search optimal DNN architectures for AMC to maximize classification accuracy and minimize network complexity. We show that BO-NSMA, with a small initial population of six individuals and only ten generations, finds a DNN architecture that outperforms all human-crafted State-of-the-Art (SoA) models. BO-NSMA discovered the first low-complexity Convolutional Neural Network (CNN)-based model, which achieves slightly better performance than costly Recurrent Neural Network (RNN)-based approaches, allowing a 2.8-fold reduction in network complexity with 0.7% performance improvement. Compared to its counterparts from Network Architecture Search (NAS), BO-NSMA finds the best architecture, which achieves up to 18.24% accuracy gain and up to a 78.71-fold reduction in network complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification

Perenda¹,

Rajendran²,

Bovet³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Several studies have suggested integrating MH algorithms to GD with BP algorithm. Bakhshi et al [121] proposed GA to explore a suitable CNN architecture tune hyperparameters such as learning rates, number of layers. In the method, the hyperparameters and parameters (i.e., weights) were optimized by GA and BP algorithms, respectively.…”

Section: ) Deep Learning Based On Hybrid Meta-heuristics and Gradient Descent Algorithmsmentioning

confidence: 99%

A Review on Community Detection in Large Complex Networks from Conventional to Deep Learning Methods: A Call for the Use of Parallel Meta-Heuristic Algorithms

et al. 2021

View full text Add to dashboard Cite

Complex networks (CNs) have gained much attention in recent years due to their importance and popularity. The rapid growth in the size of CNs leads to more difficulties in the analysis of CNs tasks. Community Detection (CD) is an important multidisciplinary research area where many machine/deep learning-based methods have been applied to map CNs into a low-dimensional representation for extracting information similarity among members of CNs. Currently, Deep Learning (DL) is one of the promising methods to extract knowledge and learn information from high dimensional space and represent it in low dimensional space. However, designing an accurate and efficient DL-based CD method especially when dealing with large CNs is always an on-going research endeavor to pursue. Meta-Heuristic (MH) algorithms have shown their potentials in improving DL models in terms of solution quality and computational cost. In addition, Parallel computing is a feasible solution for building efficient DL models. The algorithmic principle of MH is parallel in nature; however, its computation framework in DL training that is reported in the literature is not really implemented in a parallel computing setup. In this paper, we present a systematic review of CD in CNs from conventional machine learning to DL methods and point out the gap of applying DL-based CD methods in large CNs. In addition, the relevant studies on DL with parallel and MH approaches are reviewed and their implications on DL models are highlighted to prospect effective solutions to overcome the challenges of DL-based CD methods. We also point out research challenges in the field of CD and suggest possible future research directions. INDEX TERMSCommunity detection; Deep learning; Complex networks; Meta-heuristic algorithms; Parallel computing.

show abstract

Detection and diagnosis of brain tumors using deep learning convolutional neural networks

Gurunathan

Batri

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The detection of brain tumors in brain magnetic resonance imaging (MRI) image is an important process for preventing earlier death. This article proposes an automated computer aided method for detecting and locating the brain tumors in brain MRI images using deep learning algorithms. The proposed method has three sub modules as preprocessing, classifications and segmentation. In this article, data augmentation is used as preprocessing method. The preprocessed brain MRI images are classified into either tumor case or nontumor case using classification approach. In this brain tumor detection and segmentation process, convolutional neural networks (CNNs) classification architecture is used for classifying the brain images. The morphological based segmentation methodology is used in this article for segmenting the tumor regions in classified brain images. Further, the segmented tumor regions are diagnosed into "Mild" and "Severe" case using CNN architecture. The proposed methodology is applied on the brain images from open access dataset. The performance of the proposed system is analyzed in terms of sensitivity, specificity, and precision, F-score, Disc similarity index and tumor region segmentation accuracy on set of brain images. The simulation results of this proposed framework are verified by expert radiologist.

show abstract

Fast Automatic Optimisation of CNN Architectures for Image Classification Using Genetic Algorithm

Cited by 29 publications

References 13 publications

Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification

Evolutionary Optimization of Residual Neural Network Architectures for Modulation Classification

A Review on Community Detection in Large Complex Networks from Conventional to Deep Learning Methods: A Call for the Use of Parallel Meta-Heuristic Algorithms

Detection and diagnosis of brain tumors using deep learning convolutional neural networks

Contact Info

Product

Resources

About