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 …

ParaCM-PNet: A CNN-tokenized MLP combined parallel dual pyramid network for prostate and prostate cancer segmentation in MRI

W Wang, B Pan, Y Ai, G Li, Y Fu, Y Liu - Computers in Biology and Medicine, 2024 - Elsevier
The precise prostate gland and prostate cancer (PCa) segmentations enable the fusion of
magnetic resonance imaging (MRI) and ultrasound imaging (US) to guide robotic prostate …

Permanent pastures identification in Portugal using remote sensing and multi-level machine learning

TG Morais, T Domingos, J Falcão… - Frontiers in Remote …, 2024 - frontiersin.org
Introduction The Common Agricultural Policy (CAP) is a vital policy framework implemented
by the European Union to regulate and support agricultural production within member …

Nonlinearity Enhanced Adaptive Activation Function

D Yevick - arxiv preprint arxiv:2403.19896, 2024 - arxiv.org
A simply implemented activation function with even cubic nonlinearity is introduced that
increases the accuracy of neural networks without substantial additional computational …

Predictive Modeling of Thin Film Yield Stress Using Machine Learning: A Simulation-Based Approach

YB Ozdemir, OO Okudur, M Gonzalez… - … Mechanical and Multi …, 2024 - ieeexplore.ieee.org
In this study, an experimental and simulation-based approach is used to evaluate the yield
stress of integrated circuit (IC) industry-relevant thin film materials. An artificial neural …

Deep learning-assisted high-accuracy cell segmentation method for live-cell analysis in digital holographic microscopy

G Haojie, Z Li, Q Shen - Holography, Diffractive Optics, and …, 2025 - spiedigitallibrary.org
Quantitative phase imaging (QPI) is a valuable tool for investigating weakly absorbing
specimens, such as cells and tissues. Digital holographic microscopy (DHM), as a classical …

Drug-likeness Prediction and Fragment Extraction using Transformer-based Graph Neural Network on Traditional Chinese Medicine Molecules

M Colangelo - 2024 - webthesis.biblio.polito.it
The use of Traditional Chinese Medicine spans thousands of years, yet its integration into
modern pharmaceutical research has been limited. A major challenge is the lack of …

[PDF][PDF] Drug-likeness Prediction and Fragment Extraction using Transformer-based Graph Neural Network on Traditional Chinese Medicine Molecules

S Di Carlo - 2024 - webthesis.biblio.polito.it
Abstract The use of Traditional Chinese Medicine spans thousands of years, yet its
integration into modern pharmaceutical research has been limited [1]. A major challenge is …

[PDF][PDF] Deep Neural Networks in Drug-Target Activity Prediction and Machine Learning Assisted Docking of Ultra-Large Compound Libraries

T Sivula - 2022 - erepo.uef.fi
Deep learning and deep neural networks have been buzz-words for the past several years.
51, 52 After being sidetracked for a long time, the time was right for the self-learning …

OSPREY: Person Re-Identification in the sport of Padel: Utilizing One-Shot Person Re-identification with locally aware transformers to improve tracking

M Svensson, J Hult - 2022 - diva-portal.org
This thesis is concerned with the topic of person re-identification. Many tracking algorithms
today cannot keep track of players reentering the scene from different angles and times …