A review of neural architecture search

Baymurzina, Dilyara; Golikov, Eugene; Burtsev, Mikhail

doi:10.1016/j.neucom.2021.12.014

Cited by 65 publications

(23 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This manual tuning procedure is an iterative and time-consuming task, in order to eventually obtain good classification results. Therefore, neural architecture search methods [ 57 ] will be used in our future studies, in order to automate the design of our developed GAN classifier. Security and privacy aspects of patient data and leukemia diagnosis results will be also considered in our proposed medical IoT-based system, to be adopted for open communications and networked computing systems.…”

Section: Discussionmentioning

confidence: 99%

Intelligent Medical IoT-Enabled Automated Microscopic Image Diagnosis of Acute Blood Cancers

Karar

Alotaibi

2022

Sensors

View full text Add to dashboard Cite

Blood cancer, or leukemia, has a negative impact on the blood and/or bone marrow of children and adults. Acute lymphocytic leukemia (ALL) and acute myeloid leukemia (AML) are two sub-types of acute leukemia. The Internet of Medical Things (IoMT) and artificial intelligence have allowed for the development of advanced technologies to assist in recently introduced medical procedures. Hence, in this paper, we propose a new intelligent IoMT framework for the automated classification of acute leukemias using microscopic blood images. The workflow of our proposed framework includes three main stages, as follows. First, blood samples are collected by wireless digital microscopy and sent to a cloud server. Second, the cloud server carries out automatic identification of the blood conditions—either leukemias or healthy—utilizing our developed generative adversarial network (GAN) classifier. Finally, the classification results are sent to a hematologist for medical approval. The developed GAN classifier was successfully evaluated on two public data sets: ALL-IDB and ASH image bank. It achieved the best accuracy scores of 98.67% for binary classification (ALL or healthy) and 95.5% for multi-class classification (ALL, AML, and normal blood cells), when compared with existing state-of-the-art methods. The results of this study demonstrate the feasibility of our proposed IoMT framework for automated diagnosis of acute leukemia tests. Clinical realization of this blood diagnosis system is our future work.

show abstract

Section: Discussionmentioning

confidence: 99%

Intelligent Medical IoT-Enabled Automated Microscopic Image Diagnosis of Acute Blood Cancers

Karar

Alotaibi

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The significance of NAS is to solve the tuning problem of deep learning models, which is a new approach to automate the design of network structures. As described above, with the complexity of the model, the design of the neural network architecture has shifted from manual design to automatic machine design [33]. As shown in Fig.…”

Section: B Nasmentioning

confidence: 99%

EEG-Based Sleep Stage Classification via Neural Architecture Search

Kong

Peng

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

With the improvement of quality of life, people are more and more concerned about the quality of sleep. The electroencephalogram (EEG)-based sleep stage classification is a good guide for sleep quality and sleep disorders. At this stage, most automatic staging neural networks are designed by human experts, and this process is time-consuming and laborious. In this paper, we propose a novel neural architecture search (NAS) framework based on bilevel optimization approximation for EEG-based sleep stage classification. The proposed NAS architecture mainly performs the architectural search through a bilevel optimization approximation, and the model is optimized by search space approximation and search space regularization with parameters shared among cells. Finally, we evaluated the performance of the model searched by NAS on the Sleep-EDF-20, Sleep-EDF-78 and SHHS datasets with an average accuracy of 82.7%, 80.0% and 81.9%, respectively. The experimental results show that the proposed NAS algorithm provides some reference for the subsequent automatic design of networks for sleep classification.

show abstract

“…1) Chain-Structured Space: One of the simplest search spaces is the Chain-Structured space (sometimes referred to as the Layer-Wise/Stage-Wise/Global search space [50], [147]- [149]), as seen in the iconic early works of Zoph & Le and Baker et al [56], [150], [151]. As implied by the name, the Chain-Structured space is used to sample a sequentiallybuilt network from a global space of components.…”

Section: A Search Spacesmentioning

confidence: 99%

A Review on Plastic Artificial Neural Networks: Exploring the Intersection between Neural Architecture Search and Continual Learning

Shahawy¹,

Benkhelifa²,

White³

2022

Preprint

View full text Add to dashboard Cite

Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design process remains notoriously tedious, depending primarily on intuition, experience and trial-and-error. This human-dependent process is often time-consuming and prone to errors. Furthermore, the models are generally bound to their training contexts, with no considerations of changes to their surrounding environments. Continual adaptability and automation of neural networks is of paramount importance to several domains where model accessibility is limited after deployment (e.g IoT devices, selfdriving vehicles, etc). Additionally, even accessible models require frequent maintenance post-deployment to overcome issues such as Concept/Data Drift, which can be cumbersome and restrictive. The current state of the art on adaptive ANNs is still a premature area of research; nevertheless, Neural Architecture Search (NAS), a form of AutoML, and Continual Learning (CL) have recently gained an increasing momentum in the Deep Learning research field, aiming to provide more robust and adaptive ANN development frameworks. This study is the first extensive review on the intersection between AutoML and CL, outlining research directions for the different methods that can facilitate full automation and lifelong plasticity in ANNs.

show abstract

A review of neural architecture search

Cited by 65 publications

References 19 publications

Intelligent Medical IoT-Enabled Automated Microscopic Image Diagnosis of Acute Blood Cancers

Intelligent Medical IoT-Enabled Automated Microscopic Image Diagnosis of Acute Blood Cancers

EEG-Based Sleep Stage Classification via Neural Architecture Search

A Review on Plastic Artificial Neural Networks: Exploring the Intersection between Neural Architecture Search and Continual Learning

Contact Info

Product

Resources

About