检索结果-内蒙古大学图书馆

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Wallace, Richard J. Insight Centre for Data Analytics and Department of Computer Science University College Cork Cork Ireland

ISBN: (纸本)9783031734991

We still do not have an adequate understanding of heuristic methods used for solving constraint satisfaction problems (CSPs). An example involves the effects of preprocessing, an essential means of improving CSP search. The traditional explanation for its beneficial effect is that the resulting "problem reduction" leaves fewer possibilities to explore. Recently, however, it was shown that when dynamic variable ordering heuristics are used, other factors related to domain size reduction are much more important. This paper extends this analysis and explores some implications of this new perspective. The key idea is that pattern of domain reductions produced by preprocessing transmits information that guides heuristic decisions. Treating domain reduction as a code and the set of reductions as a message of length n transmitted to the search algorithm, we distinguish two factors, message discriminability and code quality, and show that greater problem reduction enhances both. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Integrating Multimodal AI Models for Enhanced Oral Cancer Detection and Diagnosis 2

Integrating Multimodal AI Models for Enhanced Oral Cancer De...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Shantha Kumari, K. Udhya shree, S. Calarany, C. Department of Data Science and Business Systems SRM Institue of Science and Technology Kattankulathur India Department of Computer Science and Engineering Rajiv Gandhi College of Engineering and Technology Pondicherry India Department of Computer Science and Engineering Tagore Government Arts and Science College Pondicherry India

ISBN: (纸本)9798331504960

Oral cancer is a major global health issue marked by high morbidity and mortality rates, primarily due to late-stage diagnosis. This work proposes the Advanced AI models that use multimodal data for early detection and diagnosis of oral cancer. Currently, traditional machine learning algorithms coupled with deep learning algorithms such as Convolutional neural networks (CNNs), focus on image-based analysis for detecting cancer. These works are delimited with minimal robustness and input data efficacy. Through the proposed multimodal AI model, histopathological images and clinical notes of the oral cancer patients are combinedly analyzed by which diagnostic accuracy is enhanced. This framework integrates CNNs for image analysis and Transformer-based models for text analysis, with a sophisticated fusion layer for data integration. Enhanced preprocessing techniques and performance optimization through Vision Transformers (ViTs) and BERT models significantly improve sensitivity, specificity, and F1-score. The multimodal AI model achieved a sensitivity of 0.90, specificity of 0.85, and an F1-score of 0.89, outperforming previous models like SVMs, RF, and CNNs. This indicates a high accuracy in identifying both positive and negative cases, ensuring reliable diagnoses. The results demonstrate a substantial improvement over traditional methods, that lays foundations for early diagnosis. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

In-Context Learning with Representations: Contextual Generalization of Trained Transformers 38

In-Context Learning with Representations: Contextual General...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yang, Tong Huang, Yu Liang, Yingbin Chi, Yuejie Department of Electrical and Computer Engineering Carnegie Mellon University United States Department of Statistics and Data Science Wharton School University of Pennsylvania United States Department of Electrical and Computer Engineering The Ohio State University United States

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to unseen examples in a prompt, which will require the model to acquire contextual knowledge of the prompt for generalization. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks. The contextual generalization here can be attained via learning the template function for each task in-context, where all template functions lie in a linear space with m basis functions. We analyze the training dynamics of one-layer multi-head transformers to in-contextly predict unlabeled inputs given partially labeled prompts, where the labels contain Gaussian noise and the number of examples in each prompt are not sufficient to determine the template. Under mild assumptions, we show that the training loss for a one-layer multi-head transformer converges linearly to a global minimum. Moreover, the transformer effectively learns to perform ridge regression over the basis functions. To our knowledge, this study is the first provable demonstration that transformers can learn contextual (i.e., template) information to generalize to both unseen examples and tasks when prompts contain only a small number of query-answer pairs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Neural Computing-Based Access Control Protocol for AI-Driven Intelligent Flying Vehicles in Industry 5.0-Assisted Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3573-3581页

作者： Mahmood, Khalid Tariq, Tayyaba Sangaiah, Arun Kumar Ghaffar, Zahid Saleem, Muhammad Asad Shamshad, Salman National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102 2801 Lebanon University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China The University of Lahore Department of Software Engineering Lahore54590 Pakistan

The continuous revolution in Artificial Intelligence (AI) has played a significant role in the development of key consumer applications, including Industry 5.0, autonomous decision-making, fault diagnosis, etc. In practice, autonomous and intelligent robots and flying vehicles (i.e., drones) are also becoming the integral part of Industry 5.0. These vehicles are attaining significant importance nowadays because of their applications in consumer electronics. However, there may be numerous privacy issues in such an infrastructure. Nevertheless, neural computing-driven security solutions have played a significant role in overcoming the security and privacy issues of AI-driven intelligent flying vehicles. Motivated by these facts, this article presents a neural computing-based access control protocol for AI-driven flying vehicles to prevent all possible security threats. A detailed security evaluation of the devised protocol is done formally using the extensively recognized Real-Or-Random (ROR) oracle model. Similarly, the informal security analysis ensures the resistance of our scheme against various potential attacks under the assumptions of CK and DY adversarial models. Moreover, detailed performance scrutiny of the devised protocol with various existing schemes shows the robustness and supremacy of our scheme in terms of computation, communication overhead, and security attributes. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Provable Identifiability of Two-Layer ReLU Neural Networks via LASSO Regularization

引用

IEEE Transactions on Information Theory 2023年第9期69卷 5921-5935页

作者： Li, Gen Wang, Ganghua Ding, Jie University of Pennsylvania The Wharton School Department of Statistics and Data Science PhiladelphiaPA19104 United States University of Minnesota School of Statistics MinneapolisMN55455 United States

LASSO regularization is a popular regression tool to enhance the prediction accuracy of statistical models by performing variable selection through the 1 penalty, initially formulated for the linear model and its variants. In this paper, the territory of LASSO is extended to two-layer ReLU neural networks, a fashionable and powerful nonlinear regression model. Specifically, given a neural network whose output y depends only on a small subset of input x, denoted by S∗, we prove that the LASSO estimator can stably reconstruct the neural network and identify S∗ when the number of samples scales logarithmically with the input dimension. This challenging regime has been well understood for linear models while barely studied for neural networks. Our theory lies in an extended Restricted Isometry Property (RIP)-based analysis framework for two-layer ReLU neural networks, which may be of independent interest to other LASSO or neural network settings. Based on the result, we advocate a neural network-based variable selection method. Experiments on simulated and real-world datasets show promising performance of the variable selection approach compared with existing techniques. © 1963-2012 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

IN-CONTEXT LEARNING LEARNS LABEL RELATIONSHIPS BUT IS NOT CONVENTIONAL LEARNING 12

IN-CONTEXT LEARNING LEARNS LABEL RELATIONSHIPS BUT IS NOT CO...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Kossen, Jannik Gal, Yarin Rainforth, Tom OATML Department of Computer Science University of Oxford United Kingdom Department of Statistics University of Oxford United Kingdom

The predictions of Large Language Models (LLMs) on downstream tasks often improve signifcantly when including examples of the input-label relationship in the context. However, there is currently no consensus about how this in-context learning (ICL) ability of LLMs works. For example, while Xie et al. (2022) liken ICL to a general-purpose learning algorithm, Min et al. (2022b) argue ICL does not even learn label relationships from in-context examples. In this paper, we provide novel insights into how ICL leverages label information, revealing both capabilities and limitations. To ensure we obtain a comprehensive picture of ICL behavior, we study probabilistic aspects of ICL predictions and thoroughly examine the dynamics of ICL as more examples are provided. Our experiments show that ICL predictions almost always depend on in-context labels and that ICL can learn truly novel tasks in-context. However, we also fnd that ICL struggles to fully overcome prediction preferences acquired from pre-training data and, further, that ICL does not consider all in-context information equally. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Cross-Paradigm Modelling: A Study of Puzznic 36

Cross-Paradigm Modelling: A Study of Puzznic

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Espasa, Joan Gent, Ian P. Miguel, Ian Nightingale, Peter Salamon, Andras Z. Villaret, Mateu School of Computer Science University of St Andrews United Kingdom University of York Department of Computer Science United Kingdom University of Girona Department of CS Mathematics and Statistics Spain

ISBN: (纸本)9798331527235

Puzznic is a tile-matching video game published by Taito in 1989 and ported to many platforms. The player manipulates blocks in a given grid until they match when two or more blocks of the same pattern are adjacent and are removed from play. The goal is to match all patterned blocks in the grid. Puzznic is rich in structure: levels have internal platforms and the blocks are affected by gravity, leading to complex state changes and the possibility of a cascaded series of matches following each move by the player. The puzzle is therefore a significant challenge to model, motivating our study. We study Puzznic from both constraint modelling and AI Planning perspectives, identifying their complementary strengths and weaknesses for this problem. We further exploit our constraint model to produce an automated tool for instance generation, parameterised on the grid, the combination of patterned blocks, and the steps required. © 2024 IEEE.

关键词： Constraint theory

来源：评论

学校读者我要写书评

暂无评论

Product Quality Enhancement in Social Media using Emotion-Enhanced Bert (EE-BERT) Model 2

Product Quality Enhancement in Social Media using Emotion-En...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Raj Kumar, V.S. Kumaresan, T. Mythily, V. Raghavendran, N. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data science Sathyamangalam India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India Nandha Engineering College Department of Computer Science and Engineering Erode India Rmk college of Engineering and Technology Department of Artificial Intelligence and Data science Chennai India

ISBN: (纸本)9798350368413

Twitter plays an important role in understanding the consumer sentiment about the products. The advanced analytics and Natural Language Processing (NLP) are used to extract actionable insights from this data and useful for a business to improve features and address issues on time for better customer satisfaction and brand loyalty. Most of the current models suffer from a lack of effective ways to handle subtle sentiment analysis because of a lack of contextual understanding and proper feature extraction. Most traditional models cannot combine and optimize features that lead to obtaining sentiments. This leads to overfitting and problems caused by local minima. The proposed Emotion-Enhanced BERT (EE-BERT) model is an extension of the standard BERT to learn contextual embeddings in user sentiment. In this work, data preprocessing includes text cleaning, tokenization, dealing with emojis and emoticons, and lemmatization with the best quality data. The proposed work is basically a dual-stream architecture extended with butterfly optimizer. First, the advanced tokenization and semantic understanding techniques is used for extracting textual features. Second, the emotion-enhanced features extracted through emotion-hash vectorization to enhance the model's contextual awareness in social media data. This provides a unified framework that combines the feature extraction methods to enhance the accuracy in sentiment analysis. It demonstrated with an impressive accuracy of 98.2% on sentiment in posts and comments with 0.15 losses. The proposed work is free from overfitting and local minima in product quality enhancement. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Bipartite Time Series Network for data Imputation 27

Bipartite Time Series Network for Data Imputation

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Amerise, Ilaria Lucrezia Fionda, Valeria Pirrò, Giuseppe Department of Economics Statistics and Finance University of Calabria Italy Department of Mathematics and Computer Science University of Calabria Italy

ISBN: (纸本)9781643685489

The pervasive issue of missing data in statistical analysis and data science significantly impacts the integrity and accuracy of Time-Series Cross-Sectional (TSCS) datasets, extensively used in domains like health sciences and sensor applications. Traditional imputation methods are often inadequate for these datasets as they fail to address the complexities arising from cross-sectional and temporal data gaps. This paper introduces BiTSNet (Bipartite Time Series Network for data Imputation), a novel approach designed to tackle the unique challenges of TSCS datasets by leveraging a dual representation of data. BiTSNet models cross-sectional time series data as sequences of bipartite graphs, where each graph represents a specific time step, and feature values are depicted as edge weights. Thus, missing values are interpreted as missing edge feature values, allowing BiTSNet to comprehensively capture spatial relationships within each time step and temporal relationships across steps. The framework uses Graph Neural Networks (GNNs) to process spatial dependencies within these bipartite graph representations and employs Recurrent Neural Networks (RNNs) to handle temporal dependencies. This integration enables BiTSNet to learn the intricate intra-time step relationships and the inter-time step dynamics effectively. Our approach not only preserves the longitudinal and cross-sectional integrity of the data but also ensures the production of valid and insightful conclusions from the enriched dataset. We evaluated BiTSNet on several datasets and compared it against the state-of-the-art approaches with encouraging results. © 2024 The Authors.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Improved Sparse Coded Features for Automatic Identification and Discrimination of Exudates and Drusen in Retinal Fundus Images

引用

SN computer science 2025年第1期6卷 1-12页

作者： Kumar, Mukesh Rani, Kumi Department of Mathematics and Statistics University of Houston-Downtown Houston 77002 TX United States Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi-NCR Campus Ghaziabad India

Diabetic Retinopathy is a medical condition in people having diabetes in which damage occurs to the retina and can cause partial or complete vision loss. It is the most common reason for vision loss in the world. Diabetic Retinopathy is characterized by the appearance of retinal lesions such as microaneurysms, exudates, cotton wool spots, and haemorrhages. Age-Related Macular Degeneration (ARMD) is another eye disease which causes gradual loss of vision with age and is characterized by the appearance of drusen. Exudates and Drusen are known as bright lesions as they appear as yellow deposits in the retina. In this paper, we propose an automated method for the classification of bright lesions in retinal fundus images based on improved sparse coded features and Support Vector Machine (SVM). We employ Scale-Invariant Feature Transform (SIFT) to extract interesting regions in the image in the form of key points and extract local low-level features in the neighbourhoods of key-points. After that, we use the sparse coding technique to get high-level sparse coded features that are used for classification using SVM. Experimental results reveal that the proposed approach gives an accuracy, sensitivity, a specificity of 92.90%, 89.60%, 95.40% for exudate classification and 93.80%, 89.60%, 95.80% for drusen classification, with a dictionary of 300 atoms on a dataset of 1158 images. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Diabetic retinopathy Drusen Exudates Region of interest Retinal fundus images Sparse coding

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：