Three decades of activations: A comprehensive survey of 400 activation functions for neural networks

V Kunc, J Kléma - arxiv preprint arxiv:2402.09092, 2024 - arxiv.org
Neural networks have proven to be a highly effective tool for solving complex problems in
many areas of life. Recently, their importance and practical usability have further been …

A systematic literature review on binary neural networks

R Sayed, H Azmi, H Shawkey, AH Khalil… - IEEE Access, 2023 - ieeexplore.ieee.org
This paper presents an extensive literature review on Binary Neural Network (BNN). BNN
utilizes binary weights and activation function parameters to substitute the full-precision …

Activation function optimization scheme for image classification

A Rahman, L He, H Wang - Knowledge-Based Systems, 2024 - Elsevier
Activation function has a significant impact on the dynamics, convergence, and performance
of deep neural networks. The search for a consistent and high-performing activation function …

SARAF: searching for adversarial robust activation functions

M Salimi, M Loni, M Sirjani, A Cicchetti… - Proceedings of the …, 2023 - dl.acm.org
Convolutional Neural Networks (CNNs) have received great attention in the computer vision
domain. However, CNNs are vulnerable to adversarial attacks, which are manipulations of …

[HTML][HTML] Lightweight Segmentation Method for Wood Panel Images Based on Improved DeepLabV3+

X Mou, H Chen, X Yu, L Chen, Z Peng, R Wang - Electronics, 2024 - mdpi.com
Accurate and efficient pixel-wise segmentation of wood panels is crucial for enabling
machine vision technologies to optimize the sawing process. Traditional image …

Advanced deep learning-based controller for robust EV speed management

P Duraipandy, AS Kumar, SM Yousuf… - … Conference on I …, 2022 - ieeexplore.ieee.org
The significant increase in electric vehicle demand (EV) has highlighted the importance of
environment-conscious and erudite architecture for speed control methods. The speed …

[HTML][HTML] Evaluation of maturity and moisture content in fresh jujube using fractal theory and tissue images

X MA, F Zhang, H LUO, F Gao - Food Science and Technology, 2023 - SciELO Brasil
This study proposes a novel method for jujube maturity and water content determination
incorporating fractal theory. Firstly, the tissue section images of winter jujube at different …

Inference genové exprese pomocí umělých neuronových sítí

V Kunc - 2024 - search.proquest.com
Merení genové exprese je nezbytné pro porozumení bunecným procesum a stavum v
rozlicných experimentálních podmínkách, což je potreba v ruzných oblastech …

Inference genové exprese pomocí umělých neuronových sítí

K Vladimír - 2024 - dspace.cvut.cz
Merení genové exprese je nezbytné pro porozumení bunecným procesum a stavum v
rozlicných experimentálních podmínkách, což je potreba v ruzných oblastech …

Research on investment portfolio strategy based on intelligent optimization algorithm

S Chen - Proceedings of the 11th International Conference on …, 2022 - dl.acm.org
The problem of portfolio optimization calculation is a hot and difficult issue of interest. The
current research on it mainly focuses on traditional measurement methods, but these …