检索结果-内蒙古大学图书馆

The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lorello, Luca Salvatore Lippi, Marco Melacci, Stefano Department of Computer Science University of Pisa Largo B. Pontecorvo 3 Pisa56127 Italy Department of Sciences and Methods for Engineering University of Modena and Reggio Emilia via Amendola 2 Reggio Emilia42122 Italy Department of Information Engineering and Mathematics University of Siena via Roma 56 Siena53100 Italy

Artificial intelligence is continuously seeking novel challenges and benchmarks to effectively measure performance and to advance the state-of-the-art. In this paper we introduce KANDY, a benchmarking framework that can be used to generate a variety of learning and reasoning tasks inspired by Kandinsky patterns. By creating curricula of binary classification tasks with increasing complexity and with sparse supervisions, KANDY can be used to implement benchmarks for continual and semi-supervised learning, with a specific focus on symbol compositionality. Classification rules are also provided in the ground truth to enable analysis of interpretable solutions. Together with the benchmark generation pipeline, we release two curricula, an easier and a harder one, that we propose as new challenges for the research community. With a thorough experimental evaluation, we show how both state-of-the-art neural models and purely symbolic approaches struggle with solving most of the tasks, thus calling for the application of advanced neuro-symbolic methods trained over time. © 2024, CC BY-NC-SA.

关键词： Curricula

FLGAN-IDS: Intrusion Detection Using GANs with Federated Learning 2nd

学校读者我要写书评

暂无评论

FLGAN-IDS: Intrusion Detection Using GANs with Federated Le...

2nd International Conference on Intelligent Systems and Data science, ISDS 2024

作者： Sarkar, Pallab Kumar Nguyen, Huu-Hoa Farid, Dewan Md. Department of Computer Science and Engineering United International University United City Madani Avenue Badda Dhaka1212 Bangladesh College of Information and Communication Technology Can Tho University 3/2 Street Ninh Kieu District Can Tho Viet Nam

ISBN: (纸本)9789819796120

The Internet of Things (IoT) has experienced substantial growth in recent years, leading to a significant increase in the number of Internet-connected devices. This rapid expansion has raised concerns regarding the escalating frequency of cyber-attacks. So, it is of utmost importance to have an effective and reliable intrusion detection system (IDS) as part of a comprehensive defense strategy. Recent studies have demonstrated that the performance of IDS can be significantly improved by utilizing machine learning techniques. However, existing centralized techniques involve data sharing, which can increase the computational load and raise privacy concerns. In this paper, we utilize Federated Learning (FL), a distributed machine learning approach that minimizes data sharing and enhances privacy and performance. Additionally, an IDS requires a comprehensive and heterogeneous dataset with sufficient training data to achieve optimal performance. The scarcity of attack data creates an imbalance in the dataset, negatively impacting the model’s effectiveness. To address this problem, We use Generative Adversarial Networks (GANs) to augment the rare class data. Subsequently, We utilize the ANOVA feature selection method to down-sample the training dataset and obtain a rebalanced, low-dimensional dataset. In this article, we propose a novel approach to Intrusion Detection Systems (IDS) by combining Generative Adversarial Networks (GANs) and Federated Learning (FL). The proposed system, FLGAN-IDS, was experimentally evaluated using the NSL-KDD and CIC-IDS2017 datasets for binary and multi-class classification. The findings of this study demonstrate that the FLGAN-IDS model outperformed alternative methods in terms of accuracy, precision, and efficiency, exhibiting remarkable recall and F1-score metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

VILMA: A ZERO-SHOT BENCHMARK FOR LINGUISTIC AND TEMPORAL GROUNDING IN VIDEO-LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kesen, Ilker Pedrotti, Andrea Dogan, Mustafa Cafagna, Michele Acikgoz, Emre Can Parcalabescu, Letitia Calixto, Iacer Frank, Anette Gatt, Albert Erdem, Aykut Erdem, Erkut Koç University KUIS AI Center 2 Koç University Department of Computer Engineering Turkey University of Pisa Department of Computer Science Italy Institute of Information Science and Technologies "Alessandro Faedo" Italy Hacettepe University Department of Computer Engineering 6 Aselsan Research Turkey University of Malta Institute of Linguistics and Language Technology Malta Heidelberg University Department of Computational Linguistics Germany Amsterdam UMC University of Amsterdam Department of Medical Informatics Netherlands Amsterdam Public Health Methodology & Mental Health Amsterdam Netherlands Utrecht University Department of Information and Computing Sciences Netherlands

With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we present VILMA1 (Video Language Model Assessment), a task-agnostic benchmark that places the assessment of fine-grained capabilities of these models on a firm footing. Task-based evaluations, while valuable, fail to capture the complexities and specific temporal aspects of moving images that VidLMs need to process. Through carefully curated counterfactuals, VILMA offers a controlled evaluation suite that sheds light on the true potential of these models, as well as their performance gaps compared to human-level understanding. VILMA also includes proficiency tests, which assess basic capabilities deemed essential to solving the main counterfactual tests. We show that current VidLMs’ grounding abilities are no better than those of vision-language models which use static images. This is especially striking once the performance on proficiency tests is factored in. Our benchmark serves as a catalyst for future research on VidLMs, helping to highlight areas that still need to be explored. © 2023, CC BY.

关键词： Computational linguistics

Review of AlexNet for Medical Image Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tang, Wenhao Sun, Junding Wang, Shuihua Zhang, Yudong 1st School of Computer Science and Technology Henan Polytechnic University Henan Jiaozuo454000 China 2nd Department of Biological Sciences Xi’an Jiaotong-Liverpool University Jiangsu Suzhou215123 China 3rd School of Computer Science and Engineering Southeast University Jiangsu Nanjing210096 China

In recent years, the rapid development of deep learning has led to a wide range of applications in medical image classification. The variants of neural network models with ever-increasing performance share some commonalities: to try to mitigate overfitting, improve generalization, avoid gradient vanishing and exploding, etc. AlexNet first utilizes the dropout technique to ease overfitting and the ReLU activation function to prevent vanishing gradient. Therefore, we focus on AlexNet, which initially contributed significantly to Convolutional Neural Networks (CNNs) research in 2012. After reviewing over 100 papers, including those from journals and conferences, we give a narrative on the technical details, advantages, and application areas of AlexNet. © 2023, CC BY.

关键词： Convolutional neural networks

Integration of Mixture of Experts and Multimodal Generative AI in Internet of Vehicles: A Survey

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Jamalipour, Abbas Fang, Yuguang Kim, Dong In Shen, Xuemin The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia Department of Computer Science City University of Hong Kong Kowloon Hong Kong The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Generative AI (GAI) can enhance the cognitive, reasoning, and planning capabilities of intelligent modules in the Internet of Vehicles (IoV) by synthesizing augmented datasets, completing sensor data, and making sequential decisions. In addition, the mixture of experts (MoE) can enable the distributed and collaborative execution of AI models without performance degradation between connected vehicles. In this survey, we explore the integration of MoE and GAI to enable Artificial General Intelligence in IoV, which can enable the realization of full autonomy for IoV with minimal human supervision and applicability in a wide range of mobility scenarios, including environment monitoring, traffic management, and autonomous driving. In particular, we present the fundamentals of GAI, MoE, and their interplay applications in IoV. Furthermore, we discuss the potential integration of MoE and GAI in IoV, including distributed perception and monitoring, collaborative decision-making and planning, and generative modeling and simulation. Finally, we present several potential research directions for facilitating the integration. © 2024, CC BY.

关键词： Integration

Control Protocol for Entangled Pair Verification in Quantum Optical Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Vasan, Vivek Agrawal, Anuj Nico-Katz, Alexander Horgan, Jerry Bash, Boulat A. Kilper, Daniel C. Ruffini, Marco School of Computer Science and Statistics CONNECT Centre Trinity College Dublin Dublin Ireland School of Physics Trinity College Dublin Dublin Ireland Department of Electronic and Electrical Engineering CONNECT Centre Trinity College Dublin Dublin Ireland Department of Electrical and Computer Engineering University of Arizona TucsonAZ United States Trinity Quantum Alliance Unit 16 Trinity Technology and Enterprise Centre Pearse Street Dublin 2 Ireland

We consider quantum networks, where entangled-photon pairs are distributed using fibre optic links from a centralized source to entangling nodes. The entanglement is then stored (via an entanglement swap) in entangling nodes’ quantum memories until used in, e.g., distributed quantum computing, quantum key distribution, quantum sensing, and other applications. Due to the fibre loss, some photons are lost in transmission. Noise in the transmission link and the quantum memory also reduces fidelity. Thus, entangling nodes must keep updated records of photon-pair arrivals to each destination, and their use by the applications. This coordination requires classical information exchange between each entangled node pair. However, the same fibre link may not admit both classical and quantum transmissions, as the classical channels can generate enough noise (i.e., via spontaneous Raman scattering) to make the quantum link unusable. Here, we consider coordinating entanglement distribution using a standard Internet protocol (IP) network instead, and propose a control protocol to enable such. We analyse the increase in latency from transmission over an IP network, together with the effect of photon loss, quantum memory noise and buffer size, to determine the fidelity and rate of entangled pairs. We characterize the relationship between the latency of the non-ideal IP network and the decoherence time of the quantum memories, providing a comparison of promising quantum memory technologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

CASTLE: A Cascaded Spatio-Temporal Approach for Long-lead Streamflow Forecasting

学校读者我要写书评

暂无评论

CASTLE: A Cascaded Spatio-Temporal Approach for Long-lead St...

2023 IEEE International Conference on Big Data, BigData 2023

作者： Zhuang, Yong Small, David L. Flynn, Patrick D Palash, Wahid Islam, Shafiqul Chen, Ping Ding, Wei Grand Valley State University School of Computing AllendaleMI United States Verisk Extreme Event Solutions Lafayette City Center BostonMA United States University of Massachusetts Boston Department of Computer Science BostonMA United States Integrated Sustainability 1600-400 3rd Avenue Southwest CalgaryABT2P 4H2 Canada Tufts University Department of Civil and Environmental Engineering BostonMA United States

ISBN: (纸本)9798350324457

Effective early warning systems for extreme flood events in large river basins necessitate reliable long-lead streamflow forecasts. However, the inherent uncertainty within each phase of the weather system-rainfall prediction, runoff generation, and streamflow prediction-amplifies with each stage, rendering accurate long-lead streamflow estimations challenging. In response to this, our study introduces a novel deep-learning-based model, the Cascaded Spatio-Temporal Learning Deep Network (CASTLE). CASTLE synergistically integrates observed upstream precipitation, recent streamflow data, and short-term precipitation forecasts derived from a selection of quantitative climate models to produce an accurate streamflow estimate. Specifically, we employ deep residual architectures on both observed and forecasted precipitation data to model the cascading spatio-temporal processes, which begin with upstream rainfall, move to rainfall-runoff, and finally conclude with downstream discharge. Our aim is to identify hidden space-time patterns that can be used to forecast future downstream flow over extended periods. We assess CASTLE's efficacy by forecasting the downstream discharge of the Ganges River over a long lead time. Results show that our approach outperforms the current state-of-the-art streamflow forecasting models. © 2023 IEEE.

关键词：

Recognition of altered gene-gene interaction using BiLSTM in different stages of lung adenocarcinoma

学校读者我要写书评

暂无评论

Procedia computer science 2024年 235卷 1213-1221页

作者： Partho Mallick Mourani Sinha Jayanta Poray Aiswaryya Banerjee Souvik Sarkar Anupam Ghosh Department of Computer Application Techno India University West Bengal EM4 Sector-V Saltlake Kolkata 700091 India Department of Mathematics Techno India University West Bengal EM4 Sector-V Saltlake Kolkata 700091 India Department of Computer Science & Engineering Sister Nivedita University DG Block Action Area I 1/2 Newtown Kolkata 700156 India Cyber Security Solution Architect House 585 Vokshith Enclave Phase 2 Road No. 3 Gajularamaram Hyderabad Telangana 500055 India Department of ComputerScience&Engineering NetajiSubhasEngineering College Techno City Panchpota Garia Kolkata 700152 India

Cancer which is caused by abnormal growth or tumour snatches away millions of lives each year. Depending on the organ affected, we find various cancer types like blood, skin, lung, kidney, breast, prostrate, liver etc. Some of these are curable if diagnosis of the disease can be made early. Others like pancreatic cancer are very difficult to cure. Hence early detection is one of most important aspects of treatment. Cancer affected patient goes through several stages of the disease. There are usually four stages of cancer. The Stage 1 of cancer being the preliminary stage and stage 4 being the last stage of the disease. It has been observed that the deadliness of the disease aggravates with each stage. There is no fixed or well defined time limit for the change in the stages. It may depend on the type of cancer, the physical attributes of the patient and on external factors and life-style habits. It is usually observed that symptoms change with change in stages of the disease. We intend to find out whether there is any change in the overall relationship between the genes amongst the various stages of lung cancer patients. Long Short Term Memory (LSTM), Bidirectional Long Short Term Memory (BiLSTM) and Feed Forward Neural Network (FNN) are used for analyzing the gene dependencies. The comparative analysis of the results obtained is done using various statistical methods of correlation and regression. Analysis of the results reveal significant variance in correlation among the various stages of lung cancer, showing Stage 2 and Stage 3 to be the most strongly correlated and Stage 1 and Stage 2 being the most weakly correlated indicating the inconsistency of genetic relationship between the various stages of lung cancer.

关键词： Lung cancer Feed Forward Neural Network LSTM BiLSTM Regression Correlation Skewness Kurtosis

Functional Networks for Image Segmentation of Cutaneous Lesions with Rational Curves 15th

学校读者我要写书评

暂无评论

Functional Networks for Image Segmentation of Cutaneous Lesi...

15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020

作者： Gálvez, Akemi Fister, Iztok Fister, Iztok Iglesias, Andrés Department of Information Science Faculty of Sciences Toho University 2-2-1 Miyama Funabashi274-8510 Japan Department of Applied Mathematics and Computational Sciences University of Cantabria Santander39005 Spain Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia

ISBN: (纸本)9783030578015

This paper considers the problem of image segmentation for medical images, in particular, cutaneous lesions. Given a digital image of a skin lesion, our goal is to compute the border curve separating the lesion from the image background. This problem can be formulated as an optimization problem, where the border curve is computed through data fitting from a set of points lying on the lesion boundary. Some recent papers have applied artificial intelligence techniques to tackle this issue. However, they usually focus on the polynomial case, ignoring the more powerful (but also more difficult) case of rational curves. In this paper, we address this problem with rational Bézier curves by applying functional networks, a powerful extension of the classical neural networks. Experimental results on some benchmark medical images show that this method performs well and can be successfully applied to this problem. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation