检索结果-内蒙古大学图书馆

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

学校读者我要写书评

暂无评论

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

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 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 Wuhan430065 China

ISBN: (纸本)9798350376548

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. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

GANtron: Emotional speech synthesis with generative adversarial networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hortal, Enrique Alarcia, Rodrigo Brechard Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Speech synthesis is used in a wide variety of industries. Nonetheless, it always sounds flat or robotic. The state of the art methods that allow for prosody control are very cumbersome to use and do not allow easy tuning. To tackle some of these drawbacks, in this work we target the implementation of a text-to-speech model where the inferred speech can be tuned with the desired emotions. To do so, we use Generative Adversarial Networks (GANs) together with a sequence-to-sequence model using an attention mechanism. We evaluate four different configurations considering different inputs and training strategies, study them and prove how our best model can generate speech files that lie in the same distribution as the initial training dataset. Additionally, a new strategy to boost the training convergence by applying a guided attention loss is *** Codes 68-T07, 62H30 © 2021, CC BY-NC-SA.

关键词： Generative adversarial networks

Symbolic regression for scientific discovery: An application to wind speed forecasting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Abdellaoui, Ismail Alaoui Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Symbolic regression corresponds to an ensemble of techniques that allow to uncover an analytical equation from data. Through a closed form formula, these techniques provide great advantages such as potential scientific discovery of new laws, as well as explainability, feature engineering as well as fast inference. Similarly, deep learning based techniques has shown an extraordinary ability of modeling complex patterns. The present paper aims at applying a recent end-to-end symbolic regression technique, i.e. the equation learner (EQL), to get an analytical equation for wind speed forecasting. We show that it is possible to derive an analytical equation that can achieve reasonable accuracy for short term horizons predictions only using few number of features. © 2021, CC BY-SA.

关键词： Forecasting

A Deletable and Modifiable Blockchain Scheme Based on Record Verification Trees and the Multisignature Mechanism

学校读者我要写书评

暂无评论

Computer Modeling in engineering & Sciences 2021年第7期128卷 223-245页

作者： Daojun Han Jinyu Chen Lei Zhang Yatian Shen Yihua Gao Xueheng Wang Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng47500China Institute of Data and Knowledge Engineering Henan UniversityKaifeng47500China School of Computer and Information Engineering Henan UniversityKaifeng47500China Department of Network and Finance Agricultural Bank of China Limited Xuchang BranchXuchang461000China School of Software Pingdingshan UniversityPingdingshan467000China Department of Network and Finance Agricultural Bank of China Limited Nanyang BranchNanyang473000China

As one of the most valuable technologies,blockchains have received extensive attention from researchers and industry circles and are widely applied in various ***,data on a blockchain cannot be *** a result,it is impossible to clean invalid and sensitive data and correct erroneous ***,to a certain extent,hinders the application of blockchains in supply chains and Internet of *** address this problem,this study presents a deletable and modifiable blockchain scheme(DMBlockChain)based on record verification trees(RVTrees)and the multisignature scheme.(1)In this scheme,an RVTree structure is designed and added to the block *** RVTree can not only ensure that a record is true and valid but,owing to its unique binary structure,also verify whether modification and deletion requests are valid.(2)In DMBlockChain,the multisignature mechanism is also *** mechanism requires the stakeholders’signatures for each modification or deletion request and thus ensures that a record will not be modified arbitrarily.A user’s request is deemed valid only if it is dually verified by the RVTree and the multisignature *** analysis finds that DMBlockChain can provide a secure and valid means for modifying and deleting records in a block while ensuring the integrity of the block and that DMBlockChain can effectively save space in some scenarios that require frequent records modification.

关键词： Blockchain record verification trees multisignature DMBlockChain

Scene-Adaptive Person Search via Bilateral Modulations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Yimin Wang, Huibing Peng, Jinjia Fu, Xianping Wang, Yang School of Information Science and Technology Dalian Maritime University Dalian China School of Cyber Security and Computer Hebei University Baoding China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China

Person search aims to localize specific a target person from a gallery set of images with various scenes. As the scene of moving pedestrian changes, the captured person image inevitably bring in lots of background noise and foreground noise on the person feature, which are completely unrelated to the person identity, leading to severe performance degeneration. To address this issue, we present a Scene-Adaptive Person Search (SEAS) model by introducing bilateral modulations to simultaneously eliminate scene noise and maintain a consistent person representation to adapt to various scenes. In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware. Additionally, to mitigate the effect of foreground noise on the person feature, SEAS introduces a Foreground Modulation Network (FMN) to compute the clutter reduction offset for the person embedding based on the feature map of the scene image. By bilateral modulations on both background and foreground within an end-to-end manner, SEAS obtains consistent feature representations without scene noise. SEAS can achieve state-of-the-art (SOTA) performance on two benchmark datasets, CUHK-SYSU with 97.1% mAP and PRW with 60.5% mAP. The code is available at https://***/whbdmu/SEAS. © 2024, CC0.

关键词： Embeddings

General game heuristic prediction based on ludeme descriptions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Stephenson, Matthew Soemers, Dennis J.N.J. Piette, Éric Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

This paper investigates the performance of different general-game-playing heuristics for games in the Ludii general game system. Based on these results, we train several regression learning models to predict the performance of these heuristics based on each game’s description file. We also provide a condensed analysis of the games available in Ludii, and the different ludemes that define them. Copyright © 2021, The Authors. All rights reserved.

关键词： data mining

General board game concepts

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Éric Piette, E.P. Stephenson, Matthew Soemers, Dennis J.N.J. Browne, Cameron Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Many games often share common ideas or aspects between them, such as their rules, controls, or playing area. However, in the context of General Game Playing (GGP) for board games, this area remains under-explored. We propose to formalise the notion of "game concept", inspired by terms generally used by game players and designers. Through the Ludii General Game System, we describe concepts for several levels of abstraction, such as the game itself, the moves played, or the states reached. This new GGP feature associated with the ludeme representation of games opens many new lines of research. The creation of a hyper-agent selector, the transfer of AI learning between games, or explaining AI techniques using game terms, can all be facilitated by the use of game concepts. Other applications which can benefit from game concepts are also discussed, such as the generation of plausible reconstructed rules for incomplete ancient games, or the implementation of a board game recommender system. Copyright © 2021, The Authors. All rights reserved.

关键词： Game theory

Pancreatic Cancer Prediction Machine Learning using Multi Fusion Model

学校读者我要写书评

暂无评论

Pancreatic Cancer Prediction Machine Learning using Multi Fu...

Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC), International Conference on

作者： V. Sathiyapriya K. Nethra Devi S. Deepa M. Marimuthu P. Manikandan S. Prabu Department of Computer Science and Engineering Knowledge Institute of Technology Kakapalayam India Department of Artificial Intelligence and Data Science Gnanamani College of Technology Namakkal India School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Computing SRM Institute of Science and Technology Tiruchirappalli India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

Pancreatic cancer poses a significant challenge in early detection and treatment due to its malignant nature within the digestive tract. Recent studies, such as those conducted by the Pancreatic Cancer Action Network, predict that pancreatic cancer will rank as the world's second leading cause of cancer-related deaths in 2020. Various methods have been explored in the literature to segment pancreatic tumors and detect lesions from CT images, crucial for assessing severity. One such method is the Min-Max segmentation algorithm, which effectively removes the jaundiced sclera region from affected eyes by analysing color gradients, offering more feasible and discriminative solutions. Additionally, the utilization of Whale Optimized feature-based selection aids in extracting optimal features for optimization purposes. Through an analysis of different classification algorithms and the implementation of a suggested technique for achieving optimum solutions and maximum accuracy, the proposed work is structured into two phases. Phase I involves pre-processing and artifact removal, followed by segmentation, while Phase II focuses on feature extraction, feature selection, and classification. The initial step of pre-processing the image facilitates pixel location using intensity measures, crucial for accurate tumor segmentation and minimizing false detection. Ultimately, the proposed approach aims to design and develop an optimal feature selection strategy for classifying pancreatic cancer tumors in PET/CT images, resulting in increased classification efficiency 92% and improved cancer tumor detection rates with compare other existing approaches.

关键词： Image segmentation Accuracy Soft sensors Pancreatic cancer Medical services Feature extraction Prediction algorithms Whale optimization algorithms Classification algorithms Ensemble learning

Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yixuan Zhao, Suyun Xiong, Li Liu, Yuhan Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Renmin University of China China Engineering Research Center Ministry of Education on Database and BI China Information School Renmin University of China China Department of Computer Science Emory University United States

Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users’ attitudes need to be satisfied locally, while a strict privacy guarantee for the global model is also required centrally. Personalized Local Differential Privacy (PLDP) is suitable for preserving users’ varying local privacy, yet only provides a central privacy guarantee equivalent to the worst-case local privacy level. Thus, achieving strong central privacy as well as personalized local privacy with a utility-promising model is a challenging problem. In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model. To tighten the privacy bound, we quantify the heterogeneous contributions to the central privacy user by user. The contributions are characterized by the ability of generating "echos" from the perturbation of each user, which is carefully measured by proposed methods Neighbor Divergence and Clip-Laplace Mechanism. Furthermore, we propose a refined framework (S-APES) with the post-sparsification technique to reduce privacy loss in high-dimension scenarios. To the best of our knowledge, the impact of shuffling on personalized local privacy is considered for the first time. We provide a strong privacy amplification effect, and the bound is tighter than the baseline result based on existing methods for uniform local privacy. Experiments demonstrate that our frameworks ensure comparable or higher accuracy for the global model. © 2023, CC BY.

关键词： Learning systems