Výsledky vyhledávání

Report

Unveiling the Potential of Graph Neural Networks in SME Credit Risk Assessment

Autor: Liu, Bingyao, Li, Iris, Yao, Jianhua, Chen, Yuan, Huang, Guanming, Wang, Jiajing

This paper takes the graph neural network as the technical framework, integrates the intrinsic connections between enterprise financial indicators, and proposes a model for enterprise credit risk assessment. The main research work includes: Firstly,

Externí odkaz: http://arxiv.org/abs/2409.17909

Zobrazit plný text záznamu

Report

Research on Dynamic Data Flow Anomaly Detection based on Machine Learning

Autor: Wang, Liyang, Cheng, Yu, Gong, Hao, Hu, Jiacheng, Tang, Xirui, Li, Iris

The sophistication and diversity of contemporary cyberattacks have rendered the use of proxies, gateways, firewalls, and encrypted tunnels as a standalone defensive strategy inadequate. Consequently, the proactive identification of data anomalies has

Externí odkaz: http://arxiv.org/abs/2409.14796

Zobrazit plný text záznamu

Report

Enhancing Convolutional Neural Networks with Higher-Order Numerical Difference Methods

Autor: Wang, Qi, Gao, Zijun, Sui, Mingxiu, Mei, Taiyuan, Cheng, Xiaohan, Li, Iris

With the rise of deep learning technology in practical applications, Convolutional Neural Networks (CNNs) have been able to assist humans in solving many real-world problems. To enhance the performance of CNNs, numerous network architectures have bee

Externí odkaz: http://arxiv.org/abs/2409.04977

Zobrazit plný text záznamu

Report

Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training

Autor: Ma, Yuhan, Sun, Dan, Gao, Erdi, Sang, Ningjing, Li, Iris, Huang, Guanming

Optimization theory serves as a pivotal scientific instrument for achieving optimal system performance, with its origins in economic applications to identify the best investment strategies for maximizing benefits. Over the centuries, from the geometr

Externí odkaz: http://arxiv.org/abs/2409.04707

Zobrazit plný text záznamu

Report

Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network

Autor: Liu, Houze, Li, Iris, Liang, Yaxin, Sun, Dan, Yang, Yining, Yang, Haowei

Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also have a large demand for computing resources, which may cause convolutional neura

Externí odkaz: http://arxiv.org/abs/2406.08837

Zobrazit plný text záznamu