检索结果-内蒙古大学图书馆

Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning

Circuit Design and Efficient Simulation of Quantum Inner Pro...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Hao Xiong Yehui Tang Xinyu Ye Junchi Yan Department of Computer Science and Engineering MoE Key Lab of AI Shanghai Jiao Tong University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

For the essential operation, namely inner product (IP) as widely adopted in classic computing e.g. matrix multi-plication, its quantum counterpart: quantum inner product (QIP), has also been recently theoretically explored with a verifiable lower complexity on quantum computers. How-ever, it remains unclear for the embodiment of the quantum circuits (QC) for QIP, let alone a (thorough) evaluation of the QIP circuits, especially in a practical context in the NISQ era by applying QIP to ml via hybrid quantum-classic pipelines. In this paper, we carefully design the QIP circuits from scratch, whose complexity is in accordance with the theoretical complexity. To make the simulation tractable on classic computers, especially when it is integrated in the gradient-based hybrid ml pipelines, we further devise a highly-efficient simulation scheme by directly simulates the output state. Experiments show that the scheme acceler-ates the simulation for more than 68k times compared with the previous circuit simulator. This allows our empirical evaluation on typical machine learning tasks, ranging from supervised and self-supervised learning via neural nets, to K-Means clustering. The results show that the calculation error brought by typical quantum mechanisms would incur in general little influence on the final numerical results given sufficient qubits. However, certain tasks e.g. ranking in K-Means could be more sensitive to quantum noise.

关键词： computers Pipelines Qubit Quantum mechanics Machine learning Self-supervised learning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary 31

ChatCite: LLM Agent with Human Workflow Guidance for Compara...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Yutong Chen, Lu Liu, aiwei Yu, Kai Wen, Lijie Tsinghua University Beijing China X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

The literature review is an indispensable step in the research process. It provides the benefit of comprehending the research problem and understanding the current research situation while conducting a comparative analysis of prior works. However, literature summary is challenging and time consuming. The previous LLM-based studies on literature review mainly focused on the complete process, including literature retrieval, screening, and summarization. However, for the summarization step, simple CoT method often lacks the ability to provide extensive comparative summary. In this work, we firstly focus on the independent literature summarization step and introduce ChatCite, an LLM agent with human workflow guidance for comparative literature summary. This agent, by mimicking the human workflow, first extracts key elements from relevant literature and then generates summaries using a Reflective Incremental Mechanism. In order to better evaluate the quality of the generated summaries, we devised a LLM-based automatic evaluation metric, G-Score, in refer to the human evaluation criteria. The ChatCite agent outperformed other models in various dimensions in the experiments. The literature summaries generated by ChatCite can also be directly used for drafting literature *** code is available. © 2025 Association for Computational Linguistics.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

Floods Relevancy and Identification of Location from Twitter Posts using NLP Techniques

Floods Relevancy and Identification of Location from Twitter...

引用

2022 MediaEval Workshop, MediaEval 2022

作者： Suleman, Muhammad Asif, Muhammad Zamir, Tayyab Mehmood, Ayaz Khan, Jebran Ahmad, Nasir Ahmad, Kashif DCSE University of Engineering and Technology Peshawar Pakistan Abasyn University Islamabad Campus Pakistan Department of AI AJOU University Korea Republic of Department of Computer Science Munster Technological University Cork Ireland

This paper presents our solutions for the MediaEval 2022 task on DisasterMM. The task is composed of two subtasks, namely (i) Relevance Classification of Twitter Posts (RCTP), and (ii) Location Extraction from Twitter Texts (LETT). The RCTP subtask aims at differentiating flood-related and non-relevant social posts while LETT is a Named Entity Recognition (NER) task and aims at the extraction of location information from the text. For RCTP, we proposed four different solutions based on BERT, RoBERTa, Distil BERT, and ALBERT obtaining an F1-score of 0.7934, 0.7970, 0.7613, and 0.7924, respectively. For LETT, we used three models namely BERT, RoBERTa, and Distil BERTA obtaining an F1-score of 0.6256, 0.6744, and 0.6723, respectively. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding 41

What Improves the Generalization of Graph Transformers? A Th...

引用

41st International Conference on Machine Learning, ICml 2024

作者： Li, Hongkang Wang, Meng Ma, Tengfei Liu, Sijia Zhang, Zaixi Chen, Pin-Yu Department of Electrical Computer and System Engineering Rensselaer Polytechnic Institute TroyNY United States Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Department of Computer Science and Engineering Michigan State University East LansingMI United States MIT-IBM Watson AI Lab IBM Research MA United States Department of Computer Science and Engineering University of Science and Technology of China Anhui Hefei China IBM Thomas J. Watson Research Center Yorktown HeightsNY United States

Graph Transformers, which incorporate self-attention and positional encoding, have recently emerged as a powerful architecture for various graph learning tasks. Despite their impressive performance, the complex non-convex interactions across layers and the recursive graph structure have made it challenging to establish a theoretical foundation for learning and generalization. This study introduces the first theoretical investigation of a shallow Graph Transformer for semi-supervised node classification, comprising a self-attention layer with relative positional encoding and a two-layer perceptron. Focusing on a graph data model with discriminative nodes that determine node labels and non-discriminative nodes that are class-irrelevant, we characterize the sample complexity required to achieve a desirable generalization error by training with stochastic gradient descent (SGD). This paper provides the quantitative characterization of the sample complexity and number of iterations for convergence dependent on the fraction of discriminative nodes, the dominant patterns, and the initial model errors. Furthermore, we demonstrate that self-attention and positional encoding enhance generalization by making the attention map sparse and promoting the core neighborhood during training, which explains the superior feature representation of Graph Transformers. Our theoretical results are supported by empirical experiments on synthetic and real-world benchmarks. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models 39

Expensive Multi-Objective Bayesian Optimization Based on Dif...

引用

39th Annual AAai Conference on Artificial Intelligence, AAai 2025

作者： Li, Bingdong Di, Zixiang Lu, Yongfan Qian, Hong Wang, Feng Yang, Peng Tang, Ke Zhou, aimin Shanghai Frontiers Science Center of Molecule Intelligent Syntheses Shanghai Institute of AI for Education School of Computer Science and Technology East China Normal University Shanghai200062 China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China School of Computer Science Wuhan University Wuhan430072 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)157735897X

Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective optimization problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficult with limited function evaluations. Existing Pareto set learning algorithms may exhibit considerable instability in such expensive scenarios, leading to significant deviations between the obtained solution set and the Pareto set (PS). In this paper, we propose a novel Composite Diffusion Model based Pareto Set Learning algorithm (CDM-PSL) for expensive MOBO. CDM-PSL includes both unconditional and conditional diffusion model for generating high-quality samples efficiently. Besides, we introduce a weighting method based on information entropy to balance different objectives. This method is integrated with a guiding strategy to appropriately balancing different objectives during the optimization process. Experimental results on both synthetic and real-world problems demonstrates that CDM-PSL attains superior performance compared with state-of-the-art MOBO algorithms. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Developing Adaptive Solutions for Accurate Pneumonia Diagnosis via Chest X-Ray Analysis

Developing Adaptive Solutions for Accurate Pneumonia Diagnos...

引用

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Kiran Sunil Kumar D S Champa C H Saraswathi G Datar Vijay C P Ranjan Kumar H S Department of ECE Vidyavardhaka College of Engineering Mysuru India Anatta innovations BGS B-School Bengaluru India Department of CSE Don Bosco Instittue of Technology Bengaluru India Department of Computer Science Engineering (AI and ML) Vidyavardhaka College of Engineering Mysuru India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Chest radiography serves as a cost-effective and powerful investigative method, providing vital respiratory information crucial for pneumonia detection. Recent advancements in artificial intelligence (ai) have led to the development of ai systems by researchers and radiologists capable of accurately diagnosing pneumonia from chest X-ray images using deep neural networks. However, the robustness and adaptability of these systems, trained using empirical risk minimization (ERM), still pose significant challenges. ERM lacks the capability to discern environment-specific spurious features and consider confounders, leading to a scenario where systems appear accurate but fail when tested in new hospital settings. To address this challenge and achieve a more robust and adaptable diagnosis of pneumonia, we propose two key ideas: firstly, replacing ERM with a robust training routine such as Invariant Risk Minimization (IRM) and virtual adversarial training (v-REx) to eliminate spurious features; and secondly, introducing a novel modular architecture that separately encodes invariant features in a self-supervised manner and style confounders. We validate the impact of each contribution individually through two experiments conducted on real-world data, aiming to enhance the reliability and generalizability of pneumonia diagnosis systems. Proposed method achieves the accuracy of 90.23 % for different datasets.

关键词： Training Risk minimization Pneumonia Hospitals Transfer learning computer architecture Robustness

来源：评论

学校读者我要写书评

暂无评论

Fluent Futures: Cutting-Edge ai Techniques for Mastering English

Fluent Futures: Cutting-Edge AI Techniques for Mastering Eng...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICaiQSA 2024

作者： Lavanya, B. Subhashini, R. Mohammad, Riyaz Punithaasree, K.S. Sekhar, K.Chandra Nagaraj, P. Rajalakshmi Institute of Technology Department of English Chennai India Saveetha Engineering College Department of English Chennai India S R.K.R.Engineering College Dept of English and Foreign Languages Chinaamiram Bhimavaram India Department of English Erode India Vignan Institute of Technology and Science Dept. of BS&H Hyderabad India K.Ramakrishnan College of Engineering Department of AI & ML Tamil nadu Samayapuram India

ISBN: (纸本)9798331517953

Cutting-Edge ai Techniques for Mastering English provides a new approach to tailored feedback in English learning that has been considerably enhanced by sophisticated ai techniques. This study provides a unique strategy to generate individualized feedback utilizing BERT (Bidirectional Encoder Representations from Transformers) and a sequence-to-sequence fine-tuning mechanism. This technique uses the ELLIPSE Corpus, a huge dataset of English Language Learner (ELL) writing samples tagged with proficiency scores and thorough comments, to deliver individualized corrections and explanations. The sequence-to-sequence approach is fine-tuned to map learner input to precise feedback, addressing components of language competency such as grammar, vocabulary, and syntax. BERT's extensive contextual awareness makes it easier to identify complex mistakes and generate appropriate repairs and explanations. Personalized feedback is strengthened by tailoring it to particular learner profiles and updating it in response to student interactions and progress. The feedback's efficacy is measured using measures like as student satisfaction, gains in writing skill, and alignment with ELLIPSE Corpus proficiency results. This technique promises to provide exact, actionable, and adaptable feedback, so considerably enhancing the language learning experience and assisting learners in meeting their competence objectives. The experimental findings show that ROUGE 1 is 0.761428, ROUGE 2 is 0.65428, and ROUGE L is 0.761428, indicating the success of the suggested technique. © 2024 IEEE.

关键词： BERT ELLIPSE Corpus English Language Learning Personalized Feedback Sequence-to-Sequence Fine-Tuning

来源：评论

学校读者我要写书评

暂无评论

Strategies for Improving NL-to-FOL Translation with LLMs: Data Generation, Incremental Fine-Tuning, and Verification

arXiv

引用

arXiv 2024年

作者： Thatikonda, Ramya Keerthy Han, Jiuzhou Buntine, Wray Shareghi, Ehsan Department of Data Science & AI Monash University Australia College of Engineering and Computer Science VinUniversity Viet Nam

Logical reasoning is a fundamental task in natural language processing that presents significant challenges to Large Language Models (LLMs). The inherent characteristics of logical reasoning makes it well-suited for symbolic representations such as first-order logic (FOL). Research in symbolic logical reasoning explored FOL generation using state-of-the-art LLMs (i.e., GPT-4) to produce FOL translations of natural language (NL) statements, but errors in translation are usually not the focus. We address this by categorizing the translation errors in FOL statements generated by LLMs, specifically for deductive logical reasoning tasks. In order to make progress towards improving the quality of FOL translations for smaller language models such as LLaMA-2 13B and Mistral 7B, we create PROOFFOL, a high-quality FOL-annotated subset of ProofWriter dataset using GPT-4o. The models fine-tuned on this silver standard data achieve a significant gain in performance when compared to larger language models such as LLaMA-2 70B. In addition to improving the model using large data, we also tackle the issue of data scarcity and introduce an incremental framework encompassing of data augmentation and verification steps. In the augmentation process, a single pair of (premises, conclusion) is split into multiple new instances based on the predicates and FOLs. This data is used for fine-tuning, and the inference on this model generates FOLs with fewer errors over the model trained on the original data. Our investigation on the translation errors leads to generation of a perturbation dataset consisting of simulated NL-to-FOL translation errors and their corresponding corrections. This data is used to train a verifier, which corrects potential syntactic and semantic FOL translation errors. We demonstrate an efficient method for making the most of a limited existing human-annotated dataset. Our results show state-of-the-art performance for ProofWriter and ProntoQA datasets using PROOFFOL on

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Smart Health Care Predictions Using Machine Learning 2

Design and Analysis of Smart Health Care Predictions Using M...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICmlAS 2025

作者： Ashok kumar, V. Priyatharsini, G.Soniya Bhimaavarapu, Krishna Charaan, R.M.Dilip Konakalla, Jai Prakash Chandralekha, E. Vel Tech Rangarajan Dr.Sagunthala R& D Institute of Science and Technology Department of CSE Chennai India Dr. M.G.R. Educational And Research Institute Department of CSE Chennai India Koneru Lakshmaiah Education Foundation Department of CSE Andhra Pradesh India Swarnandhra college of engineering and technology Department of AI & ML Andhra Pradesh India

ISBN: (纸本)9798331505745

Smart Health Prediction Using Machine Learning' is a state-of-the-art, advanced system that will use high-power predictive modeling to predict diseases based on the entered symptoms. The proposed system will go through a multistage process to maintain accuracy in the predictions. First, it pre-processes the data by handling missing values and scaling features. It selects the relevant features based on symptoms from the dataset to enhance the accuracy of the prediction. The data is divided according to training and testing. The algorithm used here is SVM, since it can easily handle high complexity in data and feature space and capture the nonlinear relationships. The training of the SVM model consists of setting a suitable value for the hyperparameters such as kernel type and regularization. The model evaluation is done based on accuracy metrics and classification reports. After the training and validation, the model is deployed in real time for healthcare scenarios. Continuous monitoring and maintenance will be done to ensure accuracy and relevance of the model with respect to disease prediction. The SVM algorithm stands proud at an impressive rate of 90% as compared to other algorithms such as Random Forest, Logistic Regression, K-Nearest Neighbors, and Decision Trees. Therefore, being able to handle such complex and high-dimensional health-care prediction datasets while capturing the nonlinear data relationships with great efficiency makes the model a major choice for real-time disease forecasting. © 2025 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Resiliency in Space Autonomy: a Review

引用

Current Robotics Reports 2023年第1期4卷 1-12页

作者： Banerjee, Avijit Mukherjee, Moumita Satpute, Sumeet Nikolakopoulos, George Robotics and AI Department of Computer science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

The article provides an extensive overview on the resilient autonomy advances made across various missions, orbital or deep-space, that captures the current research approaches while investigating the possible future direction of resiliency in space autonomy. In recent years, the need for several automated operations in space applications has been rising, that ranges from the following: spacecraft proximity operations, navigation and some station keeping applications, entry, decent and landing, planetary surface exploration, etc. Also, with the rise of miniaturization concepts in spacecraft, advanced missions with multiple spacecraft platforms introduce more complex behaviours and interactions within the agents, which drives the need for higher levels of autonomy and accommodating collaborative behaviour coupled with robustness to counter unforeseen uncertainties. This collective behaviour is now referred to as resiliency in autonomy. As space missions are getting more and more complex, for example applications where a platform physically interacts with non-cooperative space objects (debris) or planetary bodies coupled with hostile, unpredictable, and extreme environments, there is a rising need for resilient autonomy solutions. Resilience with its key attributes of robustness, redundancy and resourcefulness will lead toward new and enhanced mission paradigms of space missions.

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：