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 …
A novel optimized parametric hyperbolic tangent swish activation function for 1D-CNN: application of sensor-based human activity recognition and anomaly detection
S Ankalaki, MN Thippeswamy - Multimedia Tools and Applications, 2024 - Springer
Human activity recognition (HAR) and abnormal/anomaly detection have significant
applications for health monitoring in a smart environment. Abnormal/anomaly prediction …
applications for health monitoring in a smart environment. Abnormal/anomaly prediction …
Incorporating stock prices and text for stock movement prediction based on information fusion
Q Zhang, Y Zhang, F Bao, Y Liu, C Zhang… - Engineering Applications of …, 2024 - Elsevier
Forecasting stock market via historical financial data is an important issue for market
participants because even if the prediction accuracy is only slightly improved, better trading …
participants because even if the prediction accuracy is only slightly improved, better trading …
Novel technique for the preparation and analysis of powder-based polished sections by automated optical mineralogy: Part 2–Use of deep learning approach for …
B De Castro, M Benzaazoua, S Roychowdhury… - Minerals …, 2024 - Elsevier
Automated reflected light optical microscopy represents an alternative and affordable
technique compared to automated scanning electron microscopy for quantitative …
technique compared to automated scanning electron microscopy for quantitative …
Revisiting tensor basis neural network for Reynolds stress modeling: Application to plane channel and square duct flows
Recent advances in computing power devoted to Computational Fluid Dynamics (CFD)
have opened up a new avenue for addressing the turbulence closure problem through …
have opened up a new avenue for addressing the turbulence closure problem through …
XGL-T transformer model for intelligent image captioning
Image captioning extracts multiple semantic features from an image and integrates them into
a sentence-level description. For efficient description of the captions, it becomes necessary …
a sentence-level description. For efficient description of the captions, it becomes necessary …
Prediction of crop yield in India using machine learning and hybrid deep learning models
KS Saravanan, V Bhagavathiappan - Acta Geophysica, 2024 - Springer
Crop yield prediction is one of the burgeoning research areas in the agriculture domain. The
crop yield forecasting models are developed to enhance productivity with improved decision …
crop yield forecasting models are developed to enhance productivity with improved decision …
Non-Lambertian photometric stereo via neural inverse rendering and interreflection model
Y Yang, J Liu, Y Fu, Y Ni - Optics and Lasers in Engineering, 2024 - Elsevier
Photometric stereo (PS) is an important method for 3D fine reconstruction of object surfaces,
and nonlinear mapping is the main method for solving surface normals in photometric …
and nonlinear mapping is the main method for solving surface normals in photometric …
Photonic Neuron with on Frequency-Domain ReLU Activation Function
MV Stephanie, L Pham, A Schindler… - Journal of Lightwave …, 2024 - ieeexplore.ieee.org
Driven by an exponential growth of data, neuromorphic computing has risen in popularity as
a new method for high-performance computing. The adopted neural network (NN) model …
a new method for high-performance computing. The adopted neural network (NN) model …
Residual Deformable Convolution for better image de-weathering
H Liu, A Zhang, W Zhu, B Fu, B Ding, S Xiong - Pattern Recognition, 2024 - Elsevier
Adverse weather conditions pose great challenges to computer vision tasks like detection,
segmentation, tracing et, al. in the wild. Image de-weathering aiming at removing weather …
segmentation, tracing et, al. in the wild. Image de-weathering aiming at removing weather …