Frontiers

Semi-Supervised Learning with Foundation Models for Biomedical Data Analysis: Multimodality, Generative AI, and Clinical Adaptation

Biomedical data analysis has evolved rapidly from convolutional neural network-based systems toward transformer architectures and large-scale foundation ...
Frontiers

Graph-Guided Neural Networks: Revolutionizing Anomaly Detection in Chemical Engineering

The increasing complexity of modern chemical engineering processes presents significant challenges for timely and accurate anomaly detection. Traditional ...
Scientific Research Publishing

Kohler, M. and Langer, S. (2025) Statistical Theory for Image Classification Using Deep Convolutional Neural Network with Cross-Entropy Loss under the Hierarchical Max-Pooling ...

ABSTRACT: The Rectified Linear Unit (ReLU) activation function is widely employed in deep learning (DL). ReLU shares structural similarities with censored regression and Tobit models common in ...
GitHub

dynamic-graph-convolutional-neural-networks

Research code for semantic segmentation of 3D plant point clouds using geometric deep learning, developed in collaboration with Oak Ridge National Laboratory.
IEEE

The Evolution of Convolutional Neural Network Architectures: A Review

Abstract: Convolutional Neural Networks (CNNs) are one of the most important and successful algorithmic architectures in deep learning, especially effectively in processing data with a grid-like ...
GitHub

convolutional-neural-networks

🎮 Train a Deep Q-Learning agent using TensorFlow to master Atari Breakout with efficient experience replay and modular architecture for easy customization.
Scientific Research Publishing

Research on Structural Damage Identification Method Based on Convolutional Neural Network ()

1 College of Finance and Commerce, Guangzhou Railway Polytechnic, Guangzhou, China. 2 School of Intelligent Construction and Civil Engineering, Zhongyuan University of Technology, Zhengzhou, China. 3 ...
IEEE

Research on Probabilistic Contrastive Learning and Quadratic Convolutional Neural Network for Intelligent Diagnosis of Long-Tailed Bearing Data

Abstract: Deep learning methods have demonstrated impressive effectiveness in diagnosing bearing faults. Nevertheless, their performance tends to decline significantly in the presence of long-tailed ...