Activation functions in deep learning: A comprehensive survey and benchmark

SR Dubey, SK Singh, BB Chaudhuri - Neurocomputing, 2022 - Elsevier
Neural networks have shown tremendous growth in recent years to solve numerous
problems. Various types of neural networks have been introduced to deal with different types …

Deep reinforcement learning for resource management on network slicing: A survey

JA Hurtado Sánchez, K Casilimas… - Sensors, 2022 - mdpi.com
Network Slicing and Deep Reinforcement Learning (DRL) are vital enablers for achieving
5G and 6G networks. A 5G/6G network can comprise various network slices from unique or …

The influence of the activation function in a convolution neural network model of facial expression recognition

Y Wang, Y Li, Y Song, X Rong - Applied Sciences, 2020 - mdpi.com
The convolutional neural network (CNN) has been widely used in image recognition field
due to its good performance. This paper proposes a facial expression recognition method …

A review of practical ai for remote sensing in earth sciences

B Janga, GP Asamani, Z Sun, N Cristea - Remote Sensing, 2023 - mdpi.com
Integrating Artificial Intelligence (AI) techniques with remote sensing holds great potential for
revolutionizing data analysis and applications in many domains of Earth sciences. This …

Automatic detection of sewer defects based on improved you only look once algorithm

Y Tan, R Cai, J Li, P Chen, M Wang - Automation in Construction, 2021 - Elsevier
The drainage system is an important part of civil infrastructure. However, the underground
sewage pipe will gradually suffer from defects over time, such as tree roots, deposits …

A novel direct trajectory planning approach based on generative adversarial networks and rapidly-exploring random tree

C Zhao, Y Zhu, Y Du, F Liao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Trajectory planning is essential for self-driving vehicles and has stringent requirements for
accuracy and efficiency. The existing trajectory planning methods have limitations in the …

Prediction and evaluation of fuel properties of hydrochar from waste solid biomass: Machine learning algorithm based on proposed PSO–NN model

L Mu, Z Wang, D Wu, L Zhao, H Yin - Fuel, 2022 - Elsevier
Hydrothermal carbonization is an effective and environmentally friendly biomass
pretreatment technology, which converts high moisture biomass into homogeneous, carbon …

Flow field prediction of supercritical airfoils via variational autoencoder based deep learning framework

J Wang, C He, R Li, H Chen, C Zhai, M Zhang - Physics of Fluids, 2021 - pubs.aip.org
Effective access to obtain the complex flow fields around an airfoil is crucial in improving the
quality of supercritical wings. In this study, a systematic method based on generative deep …

Optimized leaky ReLU for handwritten Arabic character recognition using convolution neural networks

BH Nayef, SNHS Abdullah, R Sulaiman… - Multimedia Tools and …, 2022 - Springer
Object classification, such as handwritten Arabic character recognition, is a computer vision
application. Deep learning techniques such as convolutional neural networks (CNNs) are …

[HTML][HTML] A survey of convolutional neural network in breast cancer

Z Zhu, SH Wang, YD Zhang - Computer modeling in engineering & …, 2023 - ncbi.nlm.nih.gov
Aims A large number of clinical trials have proved that if breast cancer is diagnosed at an
early stage, it could give patients more treatment options and improve the treatment effect …