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 convolutional neural networks for image classification: A comprehensive review

W Rawat, Z Wang - Neural computation, 2017 - ieeexplore.ieee.org
Convolutional neural networks (CNNs) have been applied to visual tasks since the late
1980s. However, despite a few scattered applications, they were dormant until the mid …

CSPNet: A new backbone that can enhance learning capability of CNN

CY Wang, HYM Liao, YH Wu… - Proceedings of the …, 2020 - openaccess.thecvf.com
Neural networks have enabled state-of-the-art approaches to achieve incredible results on
computer vision tasks such as object detection. However, such success greatly relies on …

[BOOK][B] Neural networks and deep learning

CC Aggarwal - 2018 - Springer
“Any AI smart enough to pass a Turing test is smart enough to know to fail it.”–*** Ian
McDonald Neural networks were developed to simulate the human nervous system for …

Searching for activation functions

P Ramachandran, B Zoph, QV Le - arxiv preprint arxiv:1710.05941, 2017 - arxiv.org
The choice of activation functions in deep networks has a significant effect on the training
dynamics and task performance. Currently, the most successful and widely-used activation …

Activation functions: Comparison of trends in practice and research for deep learning

C Nwankpa, W Ijomah, A Gachagan… - arxiv preprint arxiv …, 2018 - arxiv.org
Deep neural networks have been successfully used in diverse emerging domains to solve
real world complex problems with may more deep learning (DL) architectures, being …

Densely connected convolutional networks

G Huang, Z Liu, L Van Der Maaten… - Proceedings of the …, 2017 - openaccess.thecvf.com
Recent work has shown that convolutional networks can be substantially deeper, more
accurate, and efficient to train if they contain shorter connections between layers close to the …

V2x-vit: Vehicle-to-everything cooperative perception with vision transformer

R Xu, H **ang, Z Tu, X **a, MH Yang, J Ma - European conference on …, 2022 - Springer
In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to
improve the perception performance of autonomous vehicles. We present a robust …

Learning efficient convolutional networks through network slimming

Z Liu, J Li, Z Shen, G Huang, S Yan… - Proceedings of the …, 2017 - openaccess.thecvf.com
The deployment of deep convolutional neural networks (CNNs) in many real world
applications is largely hindered by their high computational cost. In this paper, we propose a …

Geometric deep learning: going beyond euclidean data

MM Bronstein, J Bruna, Y LeCun… - IEEE Signal …, 2017 - ieeexplore.ieee.org
Geometric deep learning is an umbrella term for emerging techniques attempting to
generalize (structured) deep neural models to non-Euclidean domains, such as graphs and …