检索结果-内蒙古大学图书馆

2023 International Conference on Cyber-Physical Social intelligence, ICCSI 2023

作者： Li, Ting Chen, Xiaofeng Li, Weikai Chongqing Jiaotong University Department of Mathematics Chongqing China Miit Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9798350312492

Learning from imbalanced datasets has recently received increasing research attention. Despite the remarkable results of AdaBoost in balanced situation, the imbalance problem remains to be solved. To address this, this paper proposes a novel method to improve the AdaBoost using a new error factor and a weighted voting parameter for a few classes and weak classifiers. Our method can weaken the dominant role of the majority class in iterative training by improving the classification ability of the minority class. The superiority of the proposed algorithm is finally proved theoretically and practically. Several real-world imbalance datasets in experiments as specific support, and our method outperforms previous algorithms, especially in the F-1 metric. © 2023 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding

HELPD: Mitigating Hallucination of LVLMs by Hierarchical Fee...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Yuan, Fan Qin, Chi Xu, Xiaogang Li, Piji College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798891761643

Large Vision-Language Models (LVLMs) have shown remarkable performance on many visual-language tasks. However, these models still suffer from multimodal hallucination, which means the generation of objects or content that violates the images. Many existing work detects hallucination by directly judging whether an object exists in an image, overlooking the association between the object and semantics. To address this issue, we propose Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding (HELPD). This framework incorporates hallucination feedback at both object and sentence semantic levels. Remarkably, even with a marginal degree of training, this approach can alleviate over 15% of hallucination. Simultaneously, HELPD penalizes the output logits according to the image attention window to avoid being overly affected by generated text. HELPD can be seamlessly integrated with any LVLMs. Our experiments demonstrate that the proposed framework yields favorable results across multiple hallucination benchmarks. It effectively mitigates hallucination for different LVLMs and concurrently improves their text generation quality. © 2024 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Medical Report Generation Based on Segment-Enhanced Contrastive Representation Learning 12th

Medical Report Generation Based on Segment-Enhanced Contras...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Zhao, Ruoqing Wang, Xi Dai, Hongliang Gao, Pan Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9783031446955

Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists. However, the medical report generation task poses unique challenges due to the limited availability of medical data and the presence of data bias. To maximize the utility of available data and reduce data bias, we propose MSCL (Medical image Segmentation with Contrastive Learning), a framework that utilizes the Segment Anything Model (SAM) to segment organs, abnormalities, bones, etc., and can pay more attention to the meaningful ROIs in the image to get better visual representations. Then we introduce a supervised contrastive loss that assigns more weight to reports that are semantically similar to the target while training. The design of this loss function aims to mitigate the impact of data bias and encourage the model to capture the essential features of a medical image and generate high-quality reports. Experimental results demonstrate the effectiveness of our proposed model, where we achieve state-of-the-art performance on the IU X-Ray public dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Boundary Data Augmentation for Offline Reinforcement Learning

引用

ZTE Communications 2023年第3期21卷 29-36页

作者： SHEN Jiahao JIANG Ke TAN Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106China

Offline reinforcement learning(ORL)aims to learn a rational agent purely from behavior data without any online *** of the major challenges encountered in ORL is the problem of distribution shift,i.e.,the mismatch between the knowledge of the learned policy and the reality of the underlying *** works usually handle this in a too pessimistic manner to avoid out-of-distribution(OOD)queries as much as possible,but this can influence the robustness of the agents at unseen *** this paper,we propose a simple but effective method to address this *** key idea of our method is to enhance the robustness of the new policy learned offline by weakening its confidence in highly uncertain regions,and we propose to find those regions by simulating them with modified Generative Adversarial Nets(GAN)such that the generated data not only follow the same distribution with the old experience but are very difficult to deal with by themselves,with regard to the behavior policy or some other reference *** then use this information to regularize the ORL algorithm to penalize the overconfidence behavior in these *** experiments on several publicly available offline RL benchmarks demonstrate the feasibility and effectiveness of the proposed method.

关键词： offline reinforcement learning out‐of‐distribution state robustness uncertainty

来源：评论

学校读者我要写书评

暂无评论

DouGNN: An End-to-End Deep Learning Framework for Predicting Individual Behaviors from fMRI Data 2

DouGNN: An End-to-End Deep Learning Framework for Predicting...

引用

2nd International Conference on Image Processing, Computer Vision and machine Learning, ICICML 2023

作者： Cao, Qumei Wen, Xuyun MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9798350331417

Predicting individual behavior from functional connectivity (FC) using machine learning is a critical research topic in neuroscience. While various models have been proposed, they mainly focus on designing behavior prediction methods, overlooking the influence of upstream FC network construction approach on downstream tasks. In this paper, leveraging graph neural networks (GNNs), we introduce an end-to-end deep learning framework named DouGNN, aimed at learning individual behavior from fMRI data. Through joint training of two GNNs, DouGNN innovatively integrates individualized cortical parcellation (for FC network construction) and individual behavior prediction into a unified optimization model. By integrating individualized cortical parcellation, the model gains the ability to dynamically modify the subject's cortical parcellation and the downstream tasks. This enhancement enables the subsequently constructed FC networks to better represent individual-specific features and task-related characteristics, thereby significantly improving the performance of individual behavior prediction. Moreover, the generated individual-specific, task-aware cortical parcellations from this process can also help us in understanding the relationship between FC and behaviors. We conducted three representative behavior prediction experiments on the publicly available HCP dataset. The results demonstrate that DouGNN outperforms existing methods in all behavior prediction tasks, achieving superior performance and generating more functionally homogeneous individualized cortical parcellations. © 2023 IEEE.

关键词： Behavior prediction functional magnetic resonance imaging graph neural network individualized cortical parcellation

来源：评论

学校读者我要写书评

暂无评论

A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks 22

A Systematic Evaluation of Large Language Models for Natural...

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： Ni, Xuanfan Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Jiangsu Nanjing210016 China

ISBN: (纸本)9781713889892

Recent efforts have evaluated large language models (LLMs) in areas such as commonsense reasoning, mathematical reasoning, and code generation. However, to the best of our knowledge, no work has specifically investigated the performance of LLMs in natural language generation (NLG) tasks, a pivotal criterion for determining model excellence. Thus, this paper conducts a comprehensive evaluation of well-known and high-performing LLMs, namely ChatGPT, ChatGLM, T5-based models, LLaMA-based models, and Pythia-based models, in the context of NLG tasks. We select English and Chinese datasets encompassing Dialogue Generation and Text Summarization. Moreover, we propose a common evaluation setting that incorporates input templates and post-processing strategies. Our study reports both automatic results, accompanied by a detailed analysis. © 2023 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition 39

Unlocking Better Closed-Set Alignment Based on Neural Collap...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Li, Chaohua Zhang, Enhao Geng, Chuanxing Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Department of Computer Science Hong Kong Baptist University Hong Kong

ISBN: (纸本)157735897X

In recent Open-set Recognition (OSR) community, a prevailing belief is that enhancing the discriminative boundaries of closed-set classes can improve the robustness of Deep Neural Networks (DNNs) against open data during testing. Typical studies validate this implicitly by empirical evidence, without a formalized understanding of how DNNs help the closed-set features obtain more discriminative boundaries? For this, we provide an answer from the Neural Collapse (NC) perspective: DNNs align the closed-set with a Simplex Equiangular Tight Frame (ETF) structure that has geometric and mathematical interpretability. Regrettably, although NC naturally occurs in DNNs, we discover that typical studies cannot guarantee the features being learned to strictly align with the ETF. Thus, we introduce a novel concept, Fixed ETF Template (FiT), which holds an ideal structure associated with closed-set classes. To force class means and classifier vectors to align with FiT, we further design a Dual ETF (DEF) loss involving two components. Specifically, F-DEF loss is designed to align class means with FiT strictly, yielding optimal inter-class separability. Meanwhile, we extend a dual form to classifier vectors, termed C-DEF loss, which guides class means and classifier vectors to satisfy self-duality. Our theoretical analysis proves the validity of the proposed approach, and extensive experiments demonstrate that DEF achieves comparable or superior results with reduced computational resources on standard OSR benchmarks. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

AE-TPGG:a novel autoencoder-based approach for single-cell RNA-seq data imputation and dimensionality reduction

引用

Frontiers of Computer Science 2023年第3期17卷 217-234页

作者： Shuchang ZHAO Li ZHANG Xuejun LIU MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023China College of Computer Science and Technology Nanjing Forestry UniversityNanjing 210037China

Single-cell RNA sequencing(scRNA-seq)technology has become an effective tool for high-throughout transcriptomic study,which circumvents the averaging artifacts corresponding to bulk RNA-seq technology,yielding new perspectives on the cellular diversity of potential superficially homogeneous *** various sequencing techniques have decreased the amplification bias and improved capture efficiency caused by the low amount of starting material,the technical noise and biological variation are inevitably introduced into experimental process,resulting in high dropout events,which greatly hinder the downstream *** the bimodal expression pattern and the right-skewed characteristic existed in normalized scRNA-seq data,we propose a customized autoencoder based on a twopart-generalized-gamma distribution(AE-TPGG)for scRNAseq data analysis,which takes mixed discrete-continuous random variables of scRNA-seq data into account using a twopart model and utilizes the generalized gamma(GG)distribution,for fitting the positive and right-skewed continuous *** adopted autoencoder enables AE-TPGG to captures the inherent relationship between *** addition to the ability of achieving low-dimensional representation,the AETPGG model also provides a denoised imputation according to statistical characteristic of gene *** on real datasets demonstrate that our proposed model is competitive to current imputation methods and ameliorates a diverse set of typical scRNA-seq data analyses.

关键词： scRNA-seq autoencoder TPGG data imputation dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Characteristic AI Agents via Large Language Models 30

Characteristic AI Agents via Large Language Models

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Wang, Xi Dai, Hongliang Gao, Shen Li, Piji College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China School of Computer Science and Technology Shandong University China

ISBN: (纸本)9782493814104

The advancement of Large Language Models (LLMs) has led to significant enhancements in the performance of chatbot systems. Many researchers have dedicated their efforts to the development of bringing characteristics to chatbots. While there have been commercial products for developing role-driven chatbots using LLMs, it is worth noting that academic research in this area remains relatively scarce. Our research focuses on investigating the performance of LLMs in constructing Characteristic AI Agents by simulating real-life individuals across different settings. Current investigations have primarily focused on act on roles with simple profiles. In response to this research gap, we create a benchmark for the characteristic AI agents task, including dataset, techniques, and evaluation metrics. A dataset called "Character100" is built for this benchmark, comprising the most-visited people on Wikipedia for language models to role-play. With the constructed dataset, we conduct comprehensive assessment of LLMs across various settings. In addition, we devise a set of automatic metrics for quantitative performance evaluation. The experimental results underscore the potential directions for further improvement in the capabilities of LLMs in constructing characteristic AI agents. The benchmark is available at https://***/nuaa-nlp/Character100. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

On the learning dynamics of two-layer quadratic neural networks for understanding deep learning

引用

Frontiers of Computer Science 2022年第3期16卷 77-82页

作者： Zhenghao TAN Songcan CHEN College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsMIIT Key Laboratory of Pattern Analysis and Machine IntelligenceNanjing 211106China

Deep learning performs as a powerful paradigm in many real-world applications;however,its mechanism remains much of a *** gain insights about nonlinear hierarchical deep networks,we theoretically describe the coupled nonlinear learning dynamic of the two-layer neural network with quadratic activations,extending existing results from the linear *** quadratic activation,although rarely used in practice,shares convexity with the widely used ReLU activation,thus producing similar *** this work,we focus on the case of a canonical regression problem under the standard normal distribution and use a coupled dynamical system to mimic the gradient descent method in the sense of a continuous-time limit,then use the high order moment tensor of the normal distribution to simplify these ordinary differential *** simplified system yields unexpected fixed *** existence of these non-global-optimal stable points leads to the existence of saddle points in the loss surface of the quadratic *** analysis shows there are conserved quantities during the training of the quadratic *** quantities might result in a failed learning process if the network is initialized ***,We illustrate the comparison between the numerical learning curves and the theoretical one,which reveals the two alternately appearing stages of the learning process.

关键词： learning dynamic quadratic network ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：