检索结果-内蒙古大学图书馆

2012 5th International Conference on Biomedical Engineering and Informatics, BMEI 2012

作者： Nie, Shengdong Li, Lihong Wang, Yuanjun He, Chaofan Ji, Feng Liang, Jianmei Institute of Medical Imaging Engineering University of Shanghai for Science and Technology Shanghai China Laboratory of Pattern Analysis and Machine Intelligence Shanghai Jiaotong University Shanghai China

ISBN: (纸本)9781467311816

Accurately and reliably automated segmentation of pulmonary tumors could play an important role in lung cancer diagnosis and radiation oncology work. However, it remains a very difficult task in particular for segmenting pulmonary tumors associated with sub-solid nodules that are partially obscured in lung CT images. In this study, we proposed and tested an improved weighed kernel fuzzy c-means (IWKFCM) method that incorporates vessels structure information and classes' distribution as weights to segment sub-solid pulmonary nodules. For this purpose, a ROI of a nodule in center CT slice is manually defined. The IWKFCM algorithm is applied to identify and cluster the potential nodule pixels located in this manually-defined center slice and its adjacent slices. The sub-solid nodule is then segmented and defined through 3D connected component labeling and morphological post-processing. The segmentation method was tested using a public CT dataset (LIDC) including 36 nodules. The average overlap ratio between the automated and radiologists' segmentation of nodules is 76.18%. The false-positive ratio (FPR) and false-negative ratio (FNR) are smaller. Experimental results showed that the proposed method enabled to achieve more accurate result in segmenting sub-solid pulmonary nodules. © 2012 IEEE.

关键词： Tumors

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

Deep Self-Reconstruction Sparse Canonical Correlation analysis For Brain Imaging Genetics

Deep Self-Reconstruction Sparse Canonical Correlation Analys...

引用

IEEE International Symposium on Biomedical Imaging

作者： Meiling Wang Wei Shao Shuo Huang Daoqiang Zhang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics

Brain imaging genetics is an emerging research field to explore the underlying genetic architecture of brain structure and function measured by different imaging modalities. As a bi-multivariate technique for brain imaging genetics, sparse canonical correlation analysis (SCCA) has the good ability to identify complex multi-SNP-multi-QT associations. However, for most current brain imaging genetics with SCCA, there exist three main challenges for calculating accurate bi-multivariate relationships and selecting relevant features, i.e., nonlinearity, high-dimensionality (across all 4005 network edges between 90 brain regions), and a small number of subjects. We propose a novel deep self-reconstruction sparse canonical correlation analysis (DS-SCCA) for solving mentioned challenges in brain imaging genetics problems. Specifically, we employ deep network, i.e., multiple stacked layers of nonlinear transformation, as the kernel function, and learn the self-reconstruction matrix to reconstruct the original data at the top layer of the network. The parameters of our model are iteratively learned using parametric approach, augmented Lagrange method, and stochastic gradient descent for optimization. Experimental results on ADNI dataset are given to demonstrate that our method produces improved cross-validation performances and biologically meaningful results.

关键词： Brain Correlation Image edge detection Imaging Stochastic processes Genetics Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Forgetting, Ignorance or Myopia: Revisiting key Challenges in Online Continual Learning 38

Forgetting, Ignorance or Myopia: Revisiting Key Challenges i...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xinrui Geng, Chuanxing Wan, Wenhai Li, Shao-Yuan 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 School of Computer Science and Technology Huazhong University of Science and Technology China

Online continual learning (OCL) requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better classification ability, at the cost of a much heavier training workload. They overlooked that in real-world scenarios, e.g., in high-speed data stream environments, data do not pause to accommodate slow models. In this paper, we emphasize that model throughput- defined as the maximum number of training samples that a model can process within a unit of time - is equally important. It directly limits how much data a model can utilize and presents a challenging dilemma for current methods. With this understanding, we revisit key challenges in OCL from both empirical and theoretical perspectives, highlighting two critical issues beyond the well-documented catastrophic forgetting: (i) Model's ignorance: the single-pass nature of OCL challenges models to learn effective features within constrained training time and storage capacity, leading to a trade-off between effective learning and model throughput;(ii) Model's myopia: the local learning nature of OCL on the current task leads the model to adopt overly simplified, task-specific features and excessively sparse classifier, resulting in the gap between the optimal solution for the current task and the global objective. To tackle these issues, we propose the Non-sparse Classifier Evolution framework (NsCE) to facilitate effective global discriminative feature learning with minimal time cost. NsCE integrates non-sparse maximum separation regularization and targeted experience replay techniques with the help of pre-trained models, enabling rapid acquisition of new globally discriminative features. Extensive experiments demonstrate the substantial improvements of our framework in performance, throughput and real-world practicality. © 2024 Neural information processing systems foundation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

All-around Neural Collapse for Imbalanced Classification

arXiv

引用

arXiv 2024年

作者： Zhang, Enhao Li, Chaohua Geng, Chuanxing Chen, Songcan MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China Nanjing211106 China

Neural Collapse (NC) presents an elegant geometric structure that enables individual activations (features), class means and classifier (weights) vectors to reach optimal interclass separability during the terminal phase of training on a balanced dataset. Once shifted to imbalanced classification, such an optimal structure of NC can be readily destroyed by the notorious minority collapse, where the classifier vectors corresponding to the minority classes are squeezed. In response, existing works endeavor to recover NC typically by optimizing classifiers. However, we discover that this squeezing phenomenon is not only confined to classifier vectors but also occurs with class means. Consequently, reconstructing NC solely at the classifier aspect may be futile, as the feature means remain compressed, leading to the violation of inherent self-duality in NC (i.e., class means and classifier vectors converge mutually) and incidentally, resulting in an unsatisfactory collapse of individual activations towards the corresponding class means. To shake off these dilemmas, we present a unified All-around Neural Collapse framework (AllNC), aiming to comprehensively restore NC across multiple aspects including individual activations, class means and classifier vectors. We thoroughly analyze its effectiveness and verify on multiple benchmark datasets that it achieves state-of-the-art in both balanced and imbalanced settings. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Saliency in Attention Based Convolutional Neural Network for Classification of Vertical Root Fractures 25th

Exploiting Saliency in Attention Based Convolutional Neural ...

引用

25th International Conference on pattern Recognition Workshops, ICPR 2020

作者： Xu, Zhenxing Wan, Peng Aihemaiti, Gulibire Zhang, Daoqiang MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Affiliated Stomatology Hospital of Medical School Nanjing University Nanjing China

ISBN: (纸本)9783030687625

Cone-beam computed tomography (CBCT) is widely used in clinical diagnosis of vertical root fractures (VRFs) which presents as crack on the teeth. However, manually checking the VRFs from a larger number of CBCT images is time-consuming and error-prone. Although the Convolutional Neural Networks (CNN) have achieved unprecedented progress in natural image recognition, end-to-end CNN is unsuitable to identify VRFs due to crack appears to be multi-scales and their complex relationships with surroundings tissues. We proposed a novel Feature Pyramids Attention Convolutional Neural Network (FPA-CNN), which incorporates saliency mask and multi-scale feature to boost the classification performance. Saliency map is viewed as spatial probability map where a person might look first to make a discriminative conclusion. Therefore it plays a role of high-level hint to guide the network focusing on the discriminative region. Experimental results demonstrate that our proposed FPA-CNN overcomes the challenge arised from multi-scale crack and complex contextual relationships. © 2021, Springer Nature Switzerland AG.

关键词： Cracks

来源：评论

学校读者我要写书评

暂无评论

Kernel based statistic: identifying topological differences in brain networks

引用

Intelligent Medicine 2022年第1期2卷 30-40页

作者： Kai Ma Wei Shao Qi Zhu Daoqiang Zhang College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsMIIT Key Laboratory of Pattern Analysis and Machine IntelligenceNanjingJiangsu 210016China

Background Brain network describing interconnections between brain regions contains abundant topological *** is a challenge for the existing statistical methods(e.g.,t test)to investigate the topological differences of brain *** We proposed a kernel based statistic framework for identifying topological differences in brain *** our framework,the topological similarities between paired brain networks were measured by graph ***,graph kernels are embedded into maximum mean discrepancy for calculating kernel based test *** on this test statistic,we adopted conditional Monte Carlo simulation to compute the statistical significance(i.e.,P value)and statistical *** recruited 33 patients with Alzheimer’s disease(AD),33 patients with early mild cognitive impairment(EMCI),33 patients with late mild cognitive impairment(LMCI)and 33 normal controls(NC)in our *** are no statistical differences in demographic information between patients and *** compared state-of-the-art statistical methods include t test,t squared test,two-sample permutation test and non-normal *** We applied the proposed shortest path matched kernel to our framework for investigating the statistical differences of shortest path topological structures in brain networks of AD and *** compared our method with the existing state-of-the-art statistical methods in brain network characteristic including clustering coefficient and functional connection among EMCI,LMCI,AD,and *** results indicate that our framework can capture the statistically discriminative shortest path topological structures,such as shortest path from right rolandic operculum to right supplementary motor area(P=0.00314,statistical power=0.803).In clustering coefficient and functional connection,our framework outperforms the state-of-the-art statistical methods,such as P=0.0013 and statistical power=0.83 in the analysis of AD and *** Our proposed kernel b

关键词： Brain network Conditional monte carlo Graph kernel Statistical analysis Topological difference

来源：评论

学校读者我要写书评

暂无评论

Hybrid learning scheme for modular-based phoneme recognizer

Hybrid learning scheme for modular-based phoneme recognizer

引用

International Symposium on Signal Processing and Its Applications (ISSPA)

作者： Abbas Ahmadi Fakhri Karray Mohamed Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Canada

This paper proposes a hybrid learning scheme for modular-based recognizer for a problem of phoneme recognition. The scheme is established by combining two types of classifiers which are statistical and neural network-based ones. First, an initial modular topology is built employing statistical-based classifier and then, neural network-based classifiers are used as discriminators or local experts of the modular-based recognizer. To apply modular systems, we propose a new concept called phoneme family. We utilize k-means clustering method to obtain the families. An unknown phoneme is first fed into a corresponding module through classifier selector. Next, the exact label of the phoneme is determined within the module. Encouraging results are obtained by applying the proposed method on TIMIT database.

关键词： Neural networks Automatic speech recognition pattern recognition Artificial neural networks Hidden Markov models Network topology Speech recognition machine learning Recurrent neural networks pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Opposition-based Q(λ) algorithm

Opposition-based Q(λ) algorithm

引用

International Joint Conference on Neural Networks 2006, IJCNN '06

作者： Shokri, Maryam Tizhoosh, Hamid R. Kamel, Mohamed Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo 200 University Avenue West ON N2L 3G1 Canada Pattern Analysis and Machine Intelligence Laboratory Department of Electrical and Computer Engineering University of Waterloo 200 University Avenue West ON N2L 3G1 Canada

ISBN: (纸本)0780394909

The problem of delayed reward in reinforcement learning is usually tackled by implementing the mechanism of eligibility traces. In this paper we introduce an extension of eligibility traces to solve one of the challenging problems in reinforcement learning. The concept of opposition traces is proposed in this work to deal with large state space problems in reinforcement learning applications. We combine the idea of opposition and eligibility traces to construct the oppositionbased Q(λ). The results are compared with the conventional Watkins' Q(λ) and reflect a remarkable performance increase. © 2006 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Causality-enhanced Discreted Physics-informed Neural Networks for Predicting Evolutionary Equations 33

Causality-enhanced Discreted Physics-informed Neural Network...

引用

33rd International Joint Conference on Artificial intelligence, IJCAI 2024

作者： Li, Ye Chen, Siqi Shan, Bin Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (纸本)9781956792041

Physics-informed neural networks (PINNs) have shown promising potential for solving partial differential equations (PDEs) using deep learning. However, PINNs face training difficulties for evolutionary PDEs, particularly for dynamical systems whose solutions exhibit multi-scale or turbulent behavior over time. The reason is that PINNs may violate the temporal causality property since all the temporal features in the PINNs loss are trained simultaneously. This paper proposes to use implicit time differencing schemes to enforce temporal causality, and use transfer learning to sequentially update the PINNs in space as surrogates for PDE solutions in different time frames. The evolving PINNs are better able to capture the varying complexities of the evolutionary equations, while only requiring minor updates between adjacent time frames. Our method is theoretically proven to be convergent if the time step is small and each PINN in different time frames is well-trained. In addition, we provide state-of-the-art (SOTA) numerical results for a variety of benchmarks for which existing PINNs formulations may fail or be inefficient. We demonstrate that the proposed method improves the accuracy of PINNs approximation for evolutionary PDEs and improves efficiency by a factor of 4-40x. The code is available at https://***/SiqiChen9/TL-DPINNs. © 2024 International Joint Conferences on Artificial intelligence. All rights reserved.

关键词：

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：