The Genetic Convolutional Neural Network Model Based on Random Sample

Zhining, You; Pu, Yunming

doi:10.14257/ijunesst.2015.8.11.31

Cited by 32 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the research study on metaheuristics to optimize DL approaches is rarely carried out [ 57 , 58 ]. The fusion of the Genetic Algorithm (GA) and DCNN, proposed in [ 59 ], was the first study that initiates this optimization model using metaheuristic algorithms. Their approach chooses the DCNN characteristic by the process of recombination and mutation on GA, in which the model of DCNN is considered as a chromosome in GA.…”

Section: Introductionmentioning

confidence: 99%

Pulmonary Diffuse Airspace Opacities Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks Fine-Tuned by Whale Optimizer

Wang

Gong²,

Khishe

et al. 2021

Wireless Pers Commun

View full text Add to dashboard Cite

The early diagnosis and the accurate separation of COVID-19 from non-COVID-19 cases based on pulmonary diffuse airspace opacities is one of the challenges facing researchers. Recently, researchers try to exploit the Deep Learning (DL) method’s capability to assist clinicians and radiologists in diagnosing positive COVID-19 cases from chest X-ray images. In this approach, DL models, especially Deep Convolutional Neural Networks (DCNN), propose real-time, automated effective models to detect COVID-19 cases. However, conventional DCNNs usually use Gradient Descent-based approaches for training fully connected layers. Although GD-based Training (GBT) methods are easy to implement and fast in the process, they demand numerous manual parameter tuning to make them optimal. Besides, the GBT’s procedure is inherently sequential, thereby parallelizing them with Graphics Processing Units is very difficult. Therefore, for the sake of having a real-time COVID-19 detector with parallel implementation capability, this paper proposes the use of the Whale Optimization Algorithm for training fully connected layers. The designed detector is then benchmarked on a verified dataset called COVID-Xray-5k, and the results are verified by a comparative study with classic DCNN, DUICM, and Matched Subspace classifier with Adaptive Dictionaries. The results show that the proposed model with an average accuracy of 99.06% provides 1.87% better performance than the best comparison model. The paper also considers the concept of Class Activation Map to detect the regions potentially infected by the virus. This was found to correlate with clinical results, as confirmed by experts. Although results are auspicious, further investigation is needed on a larger dataset of COVID-19 images to have a more comprehensive evaluation of accuracy rates.

show abstract

Section: Introductionmentioning

confidence: 99%

Pulmonary Diffuse Airspace Opacities Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks Fine-Tuned by Whale Optimizer

Wang

Gong²,

Khishe

et al. 2021

Wireless Pers Commun

View full text Add to dashboard Cite

show abstract

“…In particular, a deep neural network [4][5][6][7][8][9], such as a convolutional neural network (CNN), typically takes a long time to be trained well. Other intelligent training algorithms use various advanced optimization methods such as genetic algorithms [10][11][12][13][14][15][16][17], particle swarm optimization methods [18], and annealing algorithms [19] to try to find optimal hyperparameters of an ANN. However, these commonly used training algorithms take very long training time.…”

Section: Introductionmentioning

confidence: 99%

PairNets: Novel Fast Shallow Artificial Neural Networks on Partitioned Subspaces

Zhang

2020

Preprint

View full text Add to dashboard Cite

Traditionally, an artificial neural network (ANN) is trained slowly by a gradient descent algorithm such as the backpropagation algorithm since a large number of hyperparameters of the ANN need to be fine-tuned with many training epochs. To highly speed up training, we created a novel shallow 4-layer ANN called "Pairwise Neural Network" ("PairNet") with high-speed hyperparameter optimization. In addition, a value of each input is partitioned into multiple intervals, and then an n-dimensional space is partitioned into M n-dimensional subspaces. M local Pair-Nets are built in M partitioned local n-dimensional subspaces. A local PairNet is trained very quickly with only one epoch since its hyperparameters are directly optimized one-time via simply solving a system of linear equations by using the multivariate least squares fitting method. Simulation results for three regression problems indicated that the PairNet achieved much higher speeds and lower average testing mean squared errors (MSEs) for the three cases, and lower average training MSEs for two cases than the traditional ANNs. A significant future work is to develop better and faster optimization algorithms based on intelligent methods and parallel computing methods to optimize both partitioned subspaces and hyperparameters to build the fast and effective PairNets for applications in big data mining and real-time machine learning.

show abstract

“…In particular, evolutionary approaches, such as Genetic Algorithms (GAs), have been used for NAS. For example, GA was used to optimize the number of layers and the number of neurons of each layer of a CNN that used one activation function [7,8]. Also, a multi-objective GA was used for NAS by proposing a new algorithm called NSGA-Net [9].…”

Section: Introductionmentioning

confidence: 99%

“…Model comparisons (K train = 20000, K test = 7000, 20 epochs, 20 generations) CM 4 , CM 6 , CM 8 and M 10 ) without the new GA in terms of testing F1-scores for 58 cases among 60 cases (CM8 …”

mentioning

confidence: 99%

A New Compensatory Genetic Algorithm-Based Method for Effective Compressed Multi-function Convolutional Neural Network Model Selection with Multi-Objective Optimization

Zhang

2019

Preprint

View full text Add to dashboard Cite

In recent years, there have been many popular Convolutional Neural Networks (CNNs), such as Google's Inception-V4, that have performed very well for various image classification problems. These commonly used CNN models usually use the same activation function, such as RELU, for all neurons in the convolutional layers; they are "Single-function CNNs." However, SCNNs may not always be optimal for different image classification problems with different image data in terms of image classification accuracy for real-world applications. Thus, a "Multi-function CNN" (MCNN), which uses different activation functions for different neurons, has been shown to outperform a SCNN. Also, CNNs typically have very large architectures that use a lot of memory and need a lot of data in order to be trained well. As a result, they tend to have very high training and prediction times too. A smaller CNN model takes less training time, less prediction time, less power, and less memory than a larger one. An important research problem is how to automatically and efficiently find the best CNN with both high classification performance and compact architecture with high training and prediction speeds, small power usage, and small memory size for any image classification problem. It is very useful to intelligently find an effective, fast, energy-efficient, and memory-efficient "Compressed Multi-function CNN" (CMCNN) from a large number of candidate MCNNs. A new compensatory algorithm using a new genetic algorithm (GA) is created to find the best CMCNN with an ideal compensation between performance and architecture size. The optimal CMCNN has the best performance and the smallest architecture size. Simulations using the CIFAR10 dataset showed that the new compensatory algorithm could find CMCNNs that could outperform non-compressed MCNNs in terms of classification performance (F1-score), speed, power usage, and memory usage. Other effective, fast, power-efficient, and memory-efficient CMCNNs based on popular CNN architectures will be developed and optimized for image classification problems in important real-world applications, such as brain informatics and biomedical imaging.

show abstract

The Genetic Convolutional Neural Network Model Based on Random Sample

Abstract: Convolutional neural network (CNN) --the result of the training is affected by of initial

Cited by 32 publications

References 18 publications

Pulmonary Diffuse Airspace Opacities Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks Fine-Tuned by Whale Optimizer

Pulmonary Diffuse Airspace Opacities Diagnosis from Chest X-Ray Images Using Deep Convolutional Neural Networks Fine-Tuned by Whale Optimizer

PairNets: Novel Fast Shallow Artificial Neural Networks on Partitioned Subspaces

A New Compensatory Genetic Algorithm-Based Method for Effective Compressed Multi-function Convolutional Neural Network Model Selection with Multi-Objective Optimization

Contact Info

Product

Resources

About