Completely automated CNN architecture design based on blocks

Y Sun, B Xue, M Zhang, GG Yen - IEEE transactions on neural …, 2019‏ - ieeexplore.ieee.org
The performance of convolutional neural networks (CNNs) highly relies on their
architectures. In order to design a CNN with promising performance, extensive expertise in …

A self-adaptive mutation neural architecture search algorithm based on blocks

Y Xue, Y Wang, J Liang, A Slowik - IEEE Computational …, 2021‏ - ieeexplore.ieee.org
Recently, convolutional neural networks (CNNs) have achieved great success in the field of
artificial intelligence, including speech recognition, image recognition, and natural language …

Spontaneous evolution of modularity and network motifs

N Kashtan, U Alon - … of the National Academy of Sciences, 2005‏ - National Acad Sciences
Biological networks have an inherent simplicity: they are modular with a design that can be
separated into units that perform almost independently. Furthermore, they show reuse of …

Efficient decoupling-assisted evolutionary/metaheuristic framework for expensive reliability-based design optimization problems

Z Meng, AR Yıldız, S Mirjalili - Expert systems with applications, 2022‏ - Elsevier
Reliability-based design optimization (RBDO) algorithm is to minimize the objective under
the probabilistic factors. While gradient-based and classical evolutionary RBDO algorithms …

Genetic U-Net: automatically designed deep networks for retinal vessel segmentation using a genetic algorithm

J Wei, G Zhu, Z Fan, J Liu, Y Rong, J Mo… - … on Medical Imaging, 2021‏ - ieeexplore.ieee.org
Recently, many methods based on hand-designed convolutional neural networks (CNNs)
have achieved promising results in automatic retinal vessel segmentation. However, these …

Evolving block-based convolutional neural network for hyperspectral image classification

Z Lu, S Liang, Q Yang, B Du - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Deep convolutional neural network (CNN) shows excellent effectiveness on hyperspectral
image (HSI) classification. However, the architecture design of CNN requires abundant …

Design of a hybrid energy management system using designed rule‐based control strategy and genetic algorithm for the series‐parallel plug‐in hybrid electric vehicle

N Ding, K Prasad, TT Lie - International Journal of Energy …, 2021‏ - Wiley Online Library
Electric vehicle (EV) is considered as a critical requirement to the future development of
transportation. However, the battery performance in terms of power density and energy …

Multiobjective genetic algorithms applied to solve optimization problems

AHF Dias, JA De Vasconcelos - IEEE Transactions on …, 2002‏ - ieeexplore.ieee.org
In this paper, we discuss multiobjective optimization problems solved by evolutionary
algorithms. We present the nondominated sorting genetic algorithm (NSGA) to solve this …

[HTML][HTML] Evaluating genetic algorithms through the approximability hierarchy

A Muñoz, F Rubio - Journal of Computational Science, 2021‏ - Elsevier
Optimization problems frequently appear in any scientific domain. Most of the times, the
corresponding decision problem turns out to be NP-hard, and in these cases genetic …

Hermite functions and uncertainty principles for the Fourier and the windowed Fourier transforms

A Bonami, B Demange, P Jaming - 2003‏ - content.ems.press
We extend an uncertainty principle due to Beurling into a characterization of Hermite
functions. More precisely, all functions f on Rd which may be written as P (x) exp (−〈 Ax, x〉) …