Search

Convolutional neural network (CNN), as one of the mainstream deep learning models, has achieved great success in image recognition. All neurons used in CNN are based on the McCulloch‐Pitts model, which is over‐simplified. To further improve CNN's learning capacity, this paper proposes a novel dendritic CNN (DCNN), which considers the nonlinear information processing functions of dendrites in a single neuron. The superiority of DCNN is confirmed based on four widely used image recognition tasks. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has achieved very good results because large amounts of learning data have become easily available due to improvements in computer capabilities and big data. However, it has a problem that the accuracy becomes very bad for strong noise. Therefore, in this study, we compare the classification accuracy of existing mainstream neural networks, including broad learning, convolutional neural network and multilayer perceptron. Then, their performance is verified according to the experimental results by using noise‐added MNIST and Fashion MNIST database. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Deep residual network (ResNet), one of the mainstream deep learning models, has achieved groundbreaking results in various fields. However, all neurons used in ResNet are based on the McCulloch‐Pitts model which has long been criticized for its oversimplified structure. Accordingly, this paper for the first time proposes a novel dendritic residual network by considering the powerful information processing capacity of dendrites in neurons. Experimental results based on the challenging COVID‐19 prediction problem show the superiority of the proposed method in comparison with other state‐of‐the‐art ones. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

The gravitational search algorithm (GSA) is a popular optimization method inspired by celestial interactions. And the MLGSA is an outstanding variant of GSA. To improve its performance, we propose the elite‐of‐the‐elites driven five‐layered gravitational search algorithm (EFGSA). EFGSA introduces a new population layer comprising elite individuals, improving the balance between exploration and exploitation. Experimental results on the 2017 IEEE Conference on Evolutionary Computation (CEC) benchmark functions demonstrate EFGSA's superiority over the MLGSA algorithm in terms of solution quality and convergence speed. The obtained results underscore the efficacy of EFGSA in addressing optimization problems. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]