AS-NAS: Adaptive Scalable Neural Architecture Search With Reinforced Evolutionary Algorithm for Deep Learning

Zhang, Tong; Lei, Chun‐Yu; Zhang, Zongyan; Meng, Xian-Bing; Chen, C. L. Philip

doi:10.1109/tevc.2021.3061466

Cited by 63 publications

(17 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the end, the control performance has been validated by the simulation research. Future interesting topics include the intelligent control techniques [49][50][51][52][53][54] or event-triggered control 55 for controlled riser-vessel systems.…”

Section: Discussionmentioning

confidence: 99%

Adaptive robust barrier‐based control of a 3D flexible riser system subject to boundary displacement constraints

Tan

Liu

et al. 2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

This article involves an adaptive robust barrier-based control of a three-dimensional riser system subject to system uncertainties and output constraints. A barrier-based Lyapunov function and a dynamical online update technique are merged to develop new adaptive robust control schemes for dampening the vibration, compensating for parametric uncertainties, and dealing with the constraints in the system. A rigorous Lyapunov analysis is exploited to guarantee the uniformly bounded stability in the controlled system. Finally, the efficacy of the designed approach is validated via simulation results.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive robust barrier‐based control of a 3D flexible riser system subject to boundary displacement constraints

Tan

Liu

et al. 2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…The neural architecture generating (NAG) model learns from a Pareto frontier, which guides optimal architectures based on the given budget for the target system on which the resulting architecture is expected to be used. On the other hand, Zhang et al 48 addressed the problem of the non-convexity of NAS through the use of an adaptive, scalable neural architecture search method (AS-NAS). The scalability of AS-NAS was achieved through a search strategy that combined a simple reinforcement learning, namely: reinforced I-Ching divination evolutionary algorithm (IDEA) and variable-architecture encoding strategy.…”

Section: Overview Of Eosa and Review Of Related Studiesmentioning

confidence: 99%

A bioinspired neural architecture search based convolutional neural network for breast cancer detection using histopathology images

Oyelade

Ezugwu

2021

Sci Rep

View full text Add to dashboard Cite

The design of neural architecture to address the challenge of detecting abnormalities in histopathology images can leverage the gains made in the field of neural architecture search (NAS). The NAS model consists of a search space, search strategy and evaluation strategy. The approach supports the automation of deep learning (DL) based networks such as convolutional neural networks (CNN). Automating the process of CNN architecture engineering using this approach allows for finding the best performing network for learning classification problems in specific domains and datasets. However, the engineering process of NAS is often limited by the potential solutions in search space and the search strategy. This problem often narrows the possibility of obtaining best performing networks for challenging tasks such as the classification of breast cancer in digital histopathological samples. This study proposes a NAS model with a novel search space initialization algorithm and a new search strategy. We designed a block-based stochastic categorical-to-binary (BSCB) algorithm for generating potential CNN solutions into the search space. Also, we applied and investigated the performance of a new bioinspired optimization algorithm, namely the Ebola optimization search algorithm (EOSA), for the search strategy. The evaluation strategy was achieved through computation of loss function, architectural latency and accuracy. The results obtained using images from the BACH and BreakHis databases showed that our approach obtained best performing architectures with the top-5 of the architectures yielding a significant detection rate. The top-1 CNN architecture demonstrated a state-of-the-art performance of base on classification accuracy. The NAS strategy applied in this study and the resulting candidate architecture provides researchers with the most appropriate or suitable network configuration for using digital histopathology.

show abstract

“…Finally, to tackle the problems that arise due to the size of the search space (first challenge), several authors have invested time tailoring the design of the search space [5,6], providing tools to assess its quality [36] [37], and proposing techniques to adapt the search space [7,38], among others. Despite all the advances made in this regard, the initialization of the NAS algorithms (especially the population-based ones) has not received much attention.…”

Section: Neural Architecture Searchmentioning

confidence: 99%

A Data-driven Approach to Neural Architecture Search Initialization

Traoré¹,

Camero²,

Zhu³

2021

Preprint

View full text Add to dashboard Cite

Algorithmic design in neural architecture search (NAS) has received a lot of attention, aiming to improve performance and reduce computational cost. Despite the great advances made, few authors have proposed to tailor initialization techniques for NAS. However, literature shows that a good initial set of solutions facilitate finding the optima. Therefore, in this study, we propose a data-driven technique to initialize a population-based NAS algorithm. Particularly, we proposed a twostep methodology. First, we perform a calibrated clustering analysis of the search space, and second, we extract the centroids and use them to initialize a NAS algorithm. We benchmark our proposed approach against random and Latin hypercube sampling initialization using three population-based algorithms, namely a genetic algorithm, evolutionary algorithm, and aging evolution, on CIFAR-10. More specifically, we use NAS-Bench-101 to leverage the availability of NAS benchmarks. The results show that compared to random and Latin hypercube sampling, the proposed initialization technique enables achieving significant longterm improvements for two of the search baselines, and sometimes in various search scenarios (various training budget). Moreover, we analyse the distributions of solutions obtained and find that that the population provided by the data-driven initialization technique enables retrieving local optima (maxima) of high fitness and similar configurations.

show abstract

AS-NAS: Adaptive Scalable Neural Architecture Search With Reinforced Evolutionary Algorithm for Deep Learning

Cited by 63 publications

References 33 publications

Adaptive robust barrier‐based control of a 3D flexible riser system subject to boundary displacement constraints

Adaptive robust barrier‐based control of a 3D flexible riser system subject to boundary displacement constraints

A bioinspired neural architecture search based convolutional neural network for breast cancer detection using histopathology images

A Data-driven Approach to Neural Architecture Search Initialization

Contact Info

Product

Resources

About