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 …
utilizes binary weights and activation function parameters to substitute the full-precision …
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 …
many areas of life. Recently, their importance and practical usability have further been …
Activation function optimization scheme for image classification
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 …
of deep neural networks. The search for a consistent and high-performing activation function …
Saraf: Searching for adversarial robust activation functions
Convolutional Neural Networks (CNNs) have received great attention in the computer vision
domain. However, CNNs are vulnerable to adversarial attacks, which are manipulations of …
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 …
machine vision technologies to optimize the sawing process. Traditional image …
Advanced deep learning-based controller for robust EV speed management
The significant increase in electric vehicle demand (EV) has highlighted the importance of
environment-conscious and erudite architecture for speed control methods. The speed …
environment-conscious and erudite architecture for speed control methods. The speed …
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 …
current research on it mainly focuses on traditional measurement methods, but these …
[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 …
incorporating fractal theory. Firstly, the tissue section images of winter jujube at different …
Privacy protection technology for key information of power dispatching based on sensitive data
L Zhang, G Qu, M Ge, G Shen… - … Conference on Electronic …, 2023 - spiedigitallibrary.org
In recent years, with the continuous development of the electric power industry in China, the
per capita electricity consumption is increasing, and the scale of the power grid is also …
per capita electricity consumption is increasing, and the scale of the power grid is also …
Construction of Music Assisted Instruction System Based on Genetic Algorithm
F Lin, D Yuan, S Wang, L Yang, Z Mei - EAI International Conference …, 2023 - Springer
The most important purpose of standardization of digital learning resources is the reuse and
sharing of resources, so that digital resources can be exchanged in heterogeneous systems …
sharing of resources, so that digital resources can be exchanged in heterogeneous systems …