NSTL国家科技图书文献中心

1. Osteosarcoma Detection from Whole Slide Images Using Multi-Feature Non-Seed-Based Region Growing Segmentation and Feature Extraction NSTL国家科技图书文献中心

Priti Bansal | Abhishek Singhal ... - 《Neural processing letters》 - 2023,55(4) - 3671～3693 - 共23页

摘要：Out of the various types of primary bone | cancers, Osteosarcoma is one of the most common | malignant bone tumors. Children and teenagers are mostly | affected by Osteosarcoma, which weakens the strength of | their bones and sometimes may even result in death. It

关键词： Osteosarcoma | Whole slide images | Multi-feature non-seed-based region growing | Textural heterogeneity | Marine predators

2. Long Short-Term Memory Networks with Multiple Variables for Stock Market Prediction NSTL国家科技图书文献中心

Fei Gao | Jiangshe Zhang ... - 《Neural processing letters》 - 2023,55(4) - 4211～4229 - 共19页

摘要：Long short-term memory (LSTM) networks have | been successfully applied to many fields including | finance. However, when the input contains multiple | variables, a conventional LSTM does not distinguish the | contribution of different variables and cannot make full use

关键词： LSTM | Multi-variable LSTM | Stock market prediction | Statistical arbitrage

3. Label Propagation Based on Bipartite Graph NSTL国家科技图书文献中心

Yaoxing Li | Liang Bai - 《Neural processing letters》 - 2023,55(6) - 7743～7760 - 共18页

摘要：Label propagation (LP) is a popular graph | -based semi-supervised learning framework. Its | effectiveness is limited by the distribution of prior labels | . If there are no objects with prior labels in parts | of classes, label propagation has very poor

关键词： Self-constrained | Exemplar constraints | Label distribution | Bipartite graph

4. Evaluation of the Explanatory Power Of Layer-wise Relevance Propagation using Adversarial Examples NSTL国家科技图书文献中心

Tamara R. Dieter | Horst Zisgen - 《Neural processing letters》 - 2023,55(7) - 8531～8550 - 共20页

摘要：Approaches for visualizing and explaining the | decision process of convolutional neural networks (CNNs | ) have recently received increasing attention | . Particularly popular approaches are so-called saliency | methods, which aim to assign a valence to each input

关键词： Deep learning | Layer-wise relevance propagation | Adversarial examples | Explainable artificial intelligence | Saliency maps

5. Aperiodically Intermittent Control for Exponential Stabilization of Delayed Neural Networks Via Time-dependent Functional Method EI 工程索引 NSTL国家科技图书文献中心

Yingjie Fan | Xia Huang ... - 《Neural processing letters》 - 2023,55(2) - 1355～1370 - 共16页

摘要：In this paper, the exponential stabilization | problem is investigated for delayed neural networks | (DNNs) via aperiodically intermittent control. First | , a suitable time-dependent functional is | constructed in view of the features of intermittent control

关键词： Exponential stabilization | Aperiodically intermittent control | Delayed neural networks | Time-dependent functional method

Yuqiang Li | Jing Liao ... - 《Neural processing letters》 - 2023,55(5) - 5473～5498 - 共26页

摘要：Recently, graph neural networks have achieved | good performance in graph representation learning | . However, most graph neural networks only utilize node | low-frequency signals and destroy node similarity | when aggregating graph structure and node features

关键词： Graph neural networks | Node classification | Deep learning | Network representation learning

7. Mitigate Gender Bias Using Negative Multi-task Learning NSTL国家科技图书文献中心

Liyuan Gao | Huixin Zhan ... - 《Neural processing letters》 - 2023,55(8) - 11131～11146 - 共16页

摘要：Deep learning models have showcased remarkable | performances in natural language processing tasks. While much | attention has been paid to improvements in utility | , privacy leakage and social bias are two major concerns | arising in trained models. In this paper, we address

关键词： Gender bias | Selective privacy-preserving | Negative multi-task learning | Classification

8. Finite-Horizon Robust Event-Triggered Control for Nonlinear Multi-agent Systems with State Delay NSTL国家科技图书文献中心

Chen Liu | Lei Liu - 《Neural processing letters》 - 2023,55(4) - 5167～5191 - 共25页

摘要：This paper investigates the finite-horizon | robust event-triggered control for nonlinear multi | -agent systems (NMASs) with state delay. The consensus | of NMASs has been studied extensively. Robustness | , as another significant topic of NMASs, has not been

关键词： Robust event-triggered strategy | Nonlinear multi-agent systems | State delay | Optimal control | Adaptive dynamic programming

9. A Weakly Supervised Semantic Segmentation Method Based on Local Superpixel Transformation NSTL国家科技图书文献中心

Zhiming Ma | Dali Chen ... - 《Neural processing letters》 - 2023,55(9) - 12039～12060 - 共22页

摘要：Weakly supervised semantic segmentation (WSSS | ) can obtain pseudo-semantic masks through a weaker | level of supervised labels, reducing the need for | costly pixel-level annotations. However, the general | class activation map (CAM)-based pseudo-mask

关键词： Weakly supervised learning | Semantic segmentation | Superpixel | Consistency | Class activation mapping

10. HoINT: Learning Explicit and Implicit High-order Feature Interactions for Click-through Rate Prediction EI 工程索引 NSTL国家科技图书文献中心

Hongbin Dong | Xiaowei Wang - 《Neural processing letters》 - 2023,55(1) - 401～421 - 共21页

摘要：Abstract Click-through rate (CTR) prediction | is a research hotspot in the field of | recommendation systems and online advertising. Because of the | diversity, large-scale, and high real-time characteristics | of Internet data, manual feature interaction is