检索结果-内蒙古大学图书馆

Using GPT-4 to guide causal machine learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Constantinou, Anthony C. Kitson, Neville K. Zanga, Alessio research group School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom Department of Informatics Systems and Communication University of Milano - Bicocca Milan Italy Data Science and Advanced Analytics F. Hoffmann - La Roche Ltd Basel Switzerland

Since its introduction to the public, ChatGPT has had an unprecedented impact. While some experts praised AI advancements and highlighted their potential risks, others have been critical about the accuracy and usefulness of Large Language Models (LLMs). In this paper, we are interested in the ability of LLMs to identify causal relationships. We focus on the well-established GPT-4 (Turbo) and evaluate its performance under the most restrictive conditions, by isolating its ability to infer causal relationships based solely on the variable labels without being given any other context by humans, demonstrating the minimum level of effectiveness one can expect when it is provided with label-only information. We show that questionnaire participants judge the GPT-4 graphs as the most accurate in the evaluated categories, closely followed by knowledge graphs constructed by domain experts, with causal Machine Learning (ML) far behind. We use these results to highlight the important limitation of causal ML, which often produces causal graphs that violate common sense, affecting trust in them. However, we show that pairing GPT-4 with causal ML overcomes this limitation, resulting in graphical structures learnt from real data that align more closely with those identified by domain experts, compared to structures learnt by causal ML alone. Overall, our findings suggest that despite GPT-4 not being explicitly designed to reason causally, it can still be a valuable tool for causal representation, as it improves the causal discovery process of causal ML algorithms that are designed to do just that. Copyright © 2024, The Authors. All rights reserved.

关键词： knowledge graph

SPOCKMIP: Segmentation of Vessels in MRAs with Enhanced Continuity using Maximum Intensity Projection as Loss

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Radhakrishna, Chethan Chintalapati, Karthikesh Varma Kumar, Sri Chandana Hudukula Ram Sutrave, Raviteja Mattern, Hendrik Speck, Oliver Nürnberger, Andreas Chatterjee, Soumick Faculty of Computer Science Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany German Centre for Neurodegenerative Disease Magdeburg Germany Centre for Behavioural Brain Sciences Magdeburg Germany Genomics Research Centre Human Technopole Milan Italy

Identification of vessel structures of different sizes in biomedical images is crucial in the diagnosis of many neurodegenerative diseases. However, the sparsity of good-quality annotations of such images makes the task of vessel segmentation challenging. Deep learning offers an efficient way to segment vessels of different sizes by learning their high-level feature representations and the spatial continuity of such features across dimensions. Semi-supervised patch-based approaches have been effective in identifying small vessels of one to two voxels in diameter. This study focuses on improving the segmentation quality by considering the spatial correlation of the features using the Maximum Intensity Projection (MIP) as an additional loss criterion. Two methods are proposed with the incorporation of MIPs of label segmentation on the single (z-axis) and multiple perceivable axes of the 3D volume. The proposed MIP-based methods produce segmentations with improved vessel continuity, which is evident in visual examinations of ROIs. In this study, a UNet MSS with ReLU activation replaced by LeakyReLU is trained on the Study Forrest dataset. Patch-based training is improved by introducing an additional loss term, MIP loss, to penalise the predicted discontinuity of vessels. A training set of 14 volumes is selected from the StudyForrest dataset comprising of 18 7-Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) images. Then it is used to perform a five-fold cross-validation. The generalisation performance of the method is evaluated using the other unseen volumes in the dataset. It is observed that the proposed method with multi-axes MIP loss produces better quality segmentations with a median Dice of 80.245 ± 0.129. Also, the method with single-axis MIP loss produces segmentations with a median Dice of 79.749 ± 0.109. Furthermore, a visual comparison of the ROIs in the predicted segmentation reveals a significant improvement in the continuity of the vesse

关键词： Neurodegenerative diseases

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large...

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Pingfang Tian Deting Liu Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor.

关键词： Technological innovation Large language models Oral communication Signal processing Chatbots Context modeling

Empowering Software Startups with Agile Methods and Practices: A Design science Approach

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Gandomani, Taghi Javdani Nafchi, Mina Ziaei Parizi, Reza M. Department of Computer Science Shahrekord University Shahrekord Iran CHB Science and Technology Park Shahrekord Iran Data Science Research Group Department of Computer Science Shahrekord University Shahrekord Iran Department of Software Engineering and Game Development Kennesaw State University MariettaGA30060 United States

In recent years, the number of software startups is increasing rapidly and employing a proper software development methodology in these startups is a concern. Recently, these startups have been using agile software development methodologies and practices. However, due to the special conditions of these startups and the focus on producing the Minimum Viable Product, it seems that the use of these methodologies and practices is not done correctly. Accordingly, these startups face more severe challenges, making their success more difficult. The literature review shows that few studies have been done regarding the correct methods of using agile methods and practices in software startups. This research has used Design science Research Methodology (DSRM) to fill this research gap and develop agile adaptation guidelines in software startups. The developed guidelines were validated with the participation of 23 experts from 7 software startup teams through survey questionnaires and open discussion. Eventually, final guidelines containing 13 recommendations were developed in three categories: selection of agile methods and practices, preparation for adaptation, and application and adaptation of agile methods and practices. The evaluation results show the simplicity of understanding these guidelines, their usefulness, and their support for the expected agility of the software development process. © 2022, The Authors. All rights reserved.

关键词： Software design

S3Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xue Zhou, Tian Zhu, Jianqing Liu, Jialin Yuan, Kun Yao, Tao Yin, Wotao Jin, Rong Cai, Han Qin Alibaba Group BellevueWA98004 United States Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Department of Statistics and Data Science University of Central Florida OrlandoFL32816 United States Center for Machine Learning Research Peking University Beijing100871 China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai200030 China Meta Menlo ParkCA94025 United States Department of Statistics and Data Science Department of Computer Science University of Central Florida OrlandoFL32816 United States

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S3Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S3Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S3Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S3Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures. Copyright © 2024, The Authors. All rights reserved.

关键词： Musculoskeletal system

Agricultural data Privacy: Emerging platforms & strategies

学校读者我要写书评

暂无评论

Food and Humanity

Food and Humanity 2025年 4卷

作者： Gavai, Anand K. Bouzembrak, Yamine Xhani, Donika Sedrakyan, Gayane Meuwissen, Miranda P.M. Souza, Renata Guizzardi-Silva Marvin, Hans J.P. van Hillegersberg, Jos Industrial Engineering & Business Information Systems University of Twente Enschede Netherlands Information Technology Group Wageningen University and Research Wageningen Netherlands Business Economics Group Wageningen University and Research Wageningen Netherlands Research department of HAYAN Group B.V Rhenen Netherlands Jheronimus Academy of Data Science (JADS) s-Hertogenbosch Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven 5612 AP Netherlands

Background: In today's world, grappling with the dual challenges of energy scarcity and climate change, the agricultural and food supply chains are at a crucial juncture for transformation. data privacy within these sectors is increasingly significant, as the integration of advanced digital platforms becomes essential for improving efficiency and sustainability. Scope and Approach: This systematic literature review (SLR) explores the development and application of privacy-preserving data platforms specifically tailored to the agricultural and food supply chains. The review focuses on the evolving landscape of data architectures, data sovereignty, and advanced privacy-preserving techniques. Techniques such as anonymization, encryption, differential privacy, and federated learning are examined, along with the legal and ethical considerations surrounding data sharing in the context of global energy and climate-related challenges. Key Findings and Conclusions: The review synthesizes findings from a broad spectrum of studies published over the last decade, uncovering significant advancements in privacy-preserving technologies which may show their benefit for the agricultural and food sectors. It identifies dominant research trends and promising future directions for enhancing data security and sustainability. The key findings underscore the vital importance of safeguarding data privacy in these sectors, highlighting the potential of advanced privacy techniques to protect sensitive agricultural data while balancing the need for transparency and operational effectiveness. The review concludes that adopting these innovative privacy methods is crucial for fostering a more sustainable and secure future for agriculture and food systems, contributing to the global Sustainable Development Goals such as SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production) by improving precision agriculture, optimizing yields (crop and animal) and reducing food waste. © 2025 The

关键词： data Infrastructure data platforms data privacy Food systems Sustainability

Swarm Intelligence with Adaptive Neuro-Fuzzy Inference System-Based Routing Protocol for Clustered Wireless Sensor Networks

学校读者我要写书评

暂无评论

Computational Intelligence and Neuroscience 2022年第0期2022卷 7940895页

作者： A-Matarneh, Feras Mohammed Alqaralleh, Bassam A. Y. Aldhaban, Fahad Alqaralleh, Esam A. Kumar, Anil Gupta, Deepak Joshi, Gyanendra Prasad Department of Computer Science University College of Duba University of Tabuk Tabuk71491 Saudi Arabia MIS Department College of Business Administration University of Business and Technology Jeddah21448 Saudi Arabia School of Engineering Princess Sumaya University for Technology Amman11941 Jordan Data Science Research Group School of Computing DIT University Dehradun India Department of Computer Science & Engineering Maharaja Agrasen Institute of Technology Delhi India Department of Computer Science and Engineering Sejong University Seoul05006 Korea Republic of

Wireless sensor network (WSN) comprises numerous compact-sized sensor nodes which are linked to one another. Lifetime maximization of WSN is considered a challenging problem in the design of WSN since its energy-limited capacity of the inbuilt batteries exists in the sensor nodes. Earlier works have focused on the design of clustering and routing techniques to accomplish energy efficiency and thereby result in an increased lifetime of the network. The multihop route selection process can be treated as an NP-hard problem and can be solved by the use of computational intelligence techniques such as fuzzy logic and swarm intelligence (SI) algorithms. With this motivation, this article aims to focus on the design of swarm intelligence with an adaptive neuro-fuzzy inference system-based routing (SI-ANFISR) protocol for clustered WSN. The proposed SI-ANFISR technique aims to determine the cluster heads (CHs) and optimal routes for multihop communication in the network. To accomplish this, the SI-ANFISR technique primarily employs a weighted clustering algorithm to elect CHs and construct clusters. Besides, the SI-ANFISR technique involves the design of an ANFIS model for the selection process, which make use of three input parameters, namely, residual energy, node degree, and node history. In order to optimally adjust the membership function (MF) of the ANFIS model, the squirrel search algorithm (SSA) is utilized. None of the earlier works have used ANFIS with SSA for the routing process. The design of SSA to tune the MFs of the ANFIS model for optimal routing process in WSN shows the novelty of the study. The experimental validation of the SI-ANFISR technique takes place, and the results are inspected under different aspects. The simulation results highlighted the significant performance of the SI-ANFISR technique compared to the recent techniques with a maximum throughput of 43838 kbps and residual energy of 0.4800J, respectively. © 2022 Feras Mohammed A-Matarneh et al.

关键词： Routing protocols

Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chatterjee, Soumick Tummala, Pavan Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany German Center for Neurodegenerative Disease Magdeburg Germany Center for Behavioral Brain Sciences Magdeburg Germany

Neural networks, especially convolutional neural networks (CNN), are one of the most common tools these days used in computer vision. Most of these networks work with real-valued data using real-valued features. Complex-valued convolutional neural networks (CV-CNN) can preserve the algebraic structure of complex-valued input data and have the potential to learn more complex relationships between the input and the ground-truth. Although some comparisons of CNNs and CV-CNNs for different tasks have been performed in the past, a large-scale investigation comparing different models operating on different tasks has not been conducted. Furthermore, because complex features contain both real and imaginary components, CV-CNNs have double the number of trainable parameters as real-valued CNNs in terms of the actual number of trainable parameters. Whether or not the improvements in performance with CV-CNN observed in the past have been because of the complex features or just because of having double the number of trainable parameters has not yet been explored. This paper presents a comparative study of CNN, CNNx2 (CNN with double the number of trainable parameters as the CNN), and CV-CNN. The experiments were performed using seven models for two different tasks - brain tumour classification and segmentation in brain MRIs. The results have revealed that the CV-CNN models outperformed the CNN and CNNx2 models. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

Out-of-Distribution Detection by Principal Component Correspondence

学校读者我要写书评

暂无评论

Out-of-Distribution Detection by Principal Component Corresp...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoyuan Guan Zhiyong Gan Ling Deng Wei Shi Jiankang Chen Shenshen Bu Chunliang Zhao Jianfang Hu Yuren Zhou Wei-Shi Zheng Ruixuan Wang School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Network Business Group China Unicom Guangzhou China Department of Network Intelligence Pengcheng Laboratory Shenzhen China School of Data and Science Qingdao University of Science and Technology Qingdao China School of Software Engineering Sun Yat-Sen University Zhuhai China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Out-of-distribution (OOD) detection is vital for the safe application of intelligent systems in real-world scenarios. This paper proposes an enhancement to OOD detection by leveraging the consistency in cognition between two models, both pretrained on in-distribution (ID) data. Specifically, for a given test sample, we first apply Principal Component Analysis (PCA)-based projection on the feature vectors from each model. These obtained feature vectors (with correlation between dimensions decoupled by PCA projection) are then aligned using a multiple linear mapping, which is fitted using the least squares method on the training data. We hypothesize that the regression error for OOD data will be larger than that for ID data, making it a useful metric for OOD detection. Our experimental results demonstrate the effectiveness of this method. When combined with existing robust baselines, our approach achieves state-of-the-art performance in OOD detection.

关键词： Training Measurement Analytical models Training data Vectors data models Intelligent systems Facial features Principal component analysis Least mean squares methods