Evolutionary neural networks for deep learning: a review

Ma, Yongjie; Xie, Yirong

doi:10.1007/s13042-022-01578-8

Cited by 17 publications

(3 citation statements)

References 120 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This results in a search space exploration that is faster and more efficient. GA was one of the most effective ways to evolve deep neural networks [92,93]. Xie et al [11] used the traditional GA to automatically generate CNNs, proposed a novel encoding scheme on behalf of the fix-length binary string, and then generated a set of random individuals to initialize the GA. Sun et al [94] used GA to evolve the deep CNN's neural architecture and the initial connection weight value for image classification.…”

Section: Major Eas For Nasmentioning

confidence: 99%

Evolutionary Neural Architecture Search and Its Applications in Healthcare

Liu,

Li,

Zhao

et al. 2024

CMES

View full text Add to dashboard Cite

Most of the neural network architectures are based on human experience, which requires a long and tedious trial-and-error process. Neural architecture search (NAS) attempts to detect effective architectures without human intervention. Evolutionary algorithms (EAs) for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures. Using multiobjective EAs for NAS, optimal neural architectures that meet various performance criteria can be explored and discovered efficiently. Furthermore, hardware-accelerated NAS methods can improve the efficiency of the NAS. While existing reviews have mainly focused on different strategies to complete NAS, a few studies have explored the use of EAs for NAS. In this paper, we summarize and explore the use of EAs for NAS, as well as large-scale multiobjective optimization strategies and hardware-accelerated NAS methods. NAS performs well in healthcare applications, such as medical image analysis, classification of disease diagnosis, and health monitoring. EAs for NAS can automate the search process and optimize multiple objectives simultaneously in a given healthcare task. Deep neural network has been successfully used in healthcare, but it lacks interpretability. Medical data is highly sensitive, and privacy leaks are frequently reported in the healthcare industry. To solve these problems, in healthcare, we propose an interpretable neuroevolution framework based on federated learning to address search efficiency and privacy protection. Moreover, we also point out future research directions for evolutionary NAS. Overall, for researchers who want to use EAs to optimize NNs in healthcare, we analyze the advantages and disadvantages of doing so to provide detailed guidance, and propose an interpretable privacy-preserving framework for healthcare applications.

show abstract

Section: Major Eas For Nasmentioning

confidence: 99%

Evolutionary Neural Architecture Search and Its Applications in Healthcare

Liu,

Li,

Zhao

et al. 2024

CMES

View full text Add to dashboard Cite

show abstract

“…Small clusters will also be capable of rapidly construct reliable programs to imitate the actual world, collect useful information,, and direct the development of climate change and environmental policies. For the upcoming version of deep learning based medical analysis applications, new avenues will be made available [ 423 , 424 ].…”

Section: Workflowmentioning

confidence: 99%

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Iqbal

Qureshi

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

show abstract

“…Nowadays, machine learning has made significant development, especially, image segmentation based on deep learning has become a common and effective method. Convolutional neural networks (CNN) can extract features in images and perform classification, segmentation and recognition based on the obtained features [ 9 – 12 ]. Long et al [ 13 ] proposed a fully convolutional network (FCN), which is the first end-to-end image semantic segmentation network for pixel-level prediction.…”

Section: Introductionmentioning

confidence: 99%

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation

Qin

et al. 2023

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

In recent years, more attention paid to the spine caused by related diseases, spinal parsing (the multi-class segmentation of vertebrae and intervertebral disc) is an important part of the diagnosis and treatment of various spinal diseases. The more accurate the segmentation of medical images, the more convenient and quick the clinicians can evaluate and diagnose spinal diseases. Traditional medical image segmentation is often time consuming and energy consuming. In this paper, an efficient and novel automatic segmentation network model for MR spine images is designed. The proposed Inception-CBAM Unet++ (ICUnet++) model replaces the initial module with the Inception structure in the encoder-decoder stage base on Unet++ , which uses the parallel connection of multiple convolution kernels to obtain the features of different receptive fields during in the feature extraction. According to the characteristics of the attention mechanism, Attention Gate module and CBAM module are used in the network to make the attention coefficient highlight the characteristics of the local area. To evaluate the segmentation performance of network model, four evaluation metrics, namely intersection over union (IoU), dice similarity coefficient(DSC), true positive rate(TPR), positive predictive value(PPV) are used in the study. The published SpineSagT2Wdataset3 spinal MRI dataset is used during the experiments. In the experiment results, IoU reaches 83.16%, DSC is 90.32%, TPR is 90.40%, and PPV is 90.52%. It can be seen that the segmentation indicators have been significantly improved, which reflects the effectiveness of the model.

show abstract

Evolutionary neural networks for deep learning: a review

Cited by 17 publications

References 120 publications

Evolutionary Neural Architecture Search and Its Applications in Healthcare

Evolutionary Neural Architecture Search and Its Applications in Healthcare

On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation

Contact Info

Product

Resources

About