检索结果-内蒙古大学图书馆

2023 Findings of the Association for Computational Linguistics: EMNLP 2023

作者： Wang, Hongru Hu, Minda Deng, Yang Wang, Rui Mi, Fei Wang, Weichao Wang, Yasheng Kwan, Wai-Chung King, Irwin Wong, Kam-Fai Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong National University of Singapore Singapore Huawei Noah's Ark Lab Canada

ISBN: (纸本)9798891760615

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple knowledge sources selection and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses. © 2023 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification Through Speech Data Analysis

Emotion Classification Through Speech Data Analysis

引用

2023 Winter Simulation Conference, WSC 2023

作者： Marcos, Luzalen Mai, Kristiina Valter Abhari, Abdolreza Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering Resilience Engineering Lab 350 Victoria Street TorontoONM5B 2K3 Canada Lab Department of Computer Science 245 Church Street TorontoONM5B 1Z4 Canada

ISBN: (纸本)9798350369663

Good quality healthcare services require effective communication between the patient and the healthcare provider. This work will help improve the areas of healthcare systems automation and optimization by applying Speech Emotion Recognition (SER) in health consultations to prevent miscommunication between patients and healthcare providers. Crowd-Sourced Emotional Multimodal Actors Dataset (CREMA-D) was used to compare the performances of different machine learning models in classifying emotions. Before feeding the raw dataset to the models, exploratory data analysis was done to determine features that should be considered for future analysis. Our results showed that depending on the emotion, there are some syllables in the text that were emphasized or took time to be pronounced by the speaker. After data analysis, the dataset was fed into different models and determined that the Support Vector Machine (SVM) is a machine-learning model for SER. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter based Attack Detection for Adaptive Cruise Control Systems 5

Kalman Filter based Attack Detection for Adaptive Cruise Con...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Yang, Nachuan Nan, Fuhai Revadigar, Girish Shi, Ling Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Clear Water Bay Hong Kong Huawei Singapore Research Center Shield Lab Singapore

ISBN: (纸本)9798350325294

In this paper, we investigate the security issues of adaptive cruise control (ACC) systems for autonomous vehicles. Different from the research on cyber-layer security, we focus on cyber-physical system (CPS) security which incorporates the vehicle's control and dynamics into the security design. More specifically, we first analyze the longitudinal dynamics of on-road vehicles and then formulate a leader-follower model for the ACC system. Moreover, we establish a continuous-time Kalman filter for the leader-follower model and characterize its innovation's probabilistic properties. Finally, we develop multiple attack detectors based on Kalman filtering and statistical testing. The effectiveness of the proposed methods is validated via numerical simulations and experiments on Carla, an open-source platform for autonomous driving research. © 2023 IEEE.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition 1

Examining Changes in Internal Representations of Continual L...

引用

1st ContinualAI Unconference 2023

作者： Aswani, Nishant Suresh Guesmi, Amira Hanif, Muhammad Abdullah Shafique, Muhammad Department of Computer Science and Engineering New York University Tandon Brooklyn United States eBrain Lab Division of Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates

Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods have primarily focused on the final output, such as changes in the accuracy of predicted classes, overlooking the issue of representational forgetting within the model. In this paper, we propose a novel representation-based evaluation framework for CL models. This approach involves gathering internal representations from throughout the continual learning process and formulating three-dimensional tensors. The tensors are formed by stacking representations, such as layer activations, generated from several inputs and model ‘snapshots’, throughout the learning process. By conducting tensor component analysis (TCA), we aim to uncover meaningful patterns about how the internal representations evolve, expecting to highlight the merits or shortcomings of examined CL strategies. We conduct our analyses across different model architectures and importance-based continual learning strategies, with a curated task selection. Often, the results of our approach mirror the difference in performance of various CL strategies on various architectures. Ultimately, however, we found that our methodology did not directly highlight specialized clusters of neurons, nor provide an immediate understanding the evolution of filters. We believe a scaled down variation of our approach will provide insight into the benefits and pitfalls of using TCA to study continual learning dynamics. ©2023 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

LLMs as Repositories of Factual Knowledge: Limitations and Solutions

arXiv

引用

arXiv 2025年

作者： Mousavi, Seyed Mahed Alghisi, Simone Riccardi, Giuseppe Signals and Interactive Systems Lab Department of Information Engineering and Computer Science University of Trento Italy

LLMs’ sources of knowledge are data snapshots containing factual information about entities collected at different timestamps and from different media types (e.g. wikis, social media, etc.). Such unstructured knowledge is subject to change due to updates through time from past to present. Equally important are the inconsistencies and inaccuracies occurring in different information sources. Consequently, the model’s knowledge about an entity may be perturbed while training over the sequence of snapshots or at inference time, resulting in inconsistent and inaccurate model performance. In this work, we study the appropriateness of Large Language Models (LLMs) as repositories of factual knowledge. We consider twenty-four state-of-the-art LLMs that are either closed-, partially (weights), or fully (weight and training data) open-source. We evaluate their reliability in responding to time-sensitive factual questions in terms of accuracy and consistency when prompts are perturbed. We further evaluate the effectiveness of state-of-the-art methods to improve LLMs’ accuracy and consistency. We then propose "ENtity-Aware Fine-tuning" (ENAF), a soft neurosymbolic approach aimed at providing structured representation of entities during fine-tuning to improve the model’s performance. © 2025, CC BY-NC-SA.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

F-CNN: Faster CNN Exploiting Data Re-Use with Statistical Analysis 5

F-CNN: Faster CNN Exploiting Data Re-Use with Statistical An...

引用

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Alantali, Fatmah Halawani, Yasmin Mohammad, Baker Al-Qutayri, Mahmoud Khalifa University System-on-Chip Lab Electrical Engineering and Computer Science Department Abu Dhabi United Arab Emirates University of Dubai College of Engineering & Information Technology Dubai United Arab Emirates

ISBN: (纸本)9798350332674

Many of the current edge computing devices need efficient implementation of Artificial Intelligence (AI) applications due to strict latency, security and power requirements. Nonetheless, such devices, face various challenges when executing AI applications due to their limited computing and energy resources. In particular, Convolutional Neural Networks (CNN) is a popular machine learning method that derives a high-level function from being trained on various visual input examples. This paper contributes to enabling the use of CNN on resource-constrained devices offline, where a trade-off between accuracy, running time and power efficiency is verified. The paper investigates the use of minimum pre-processing methods of input data to identify nonessential computations in the convolutional layers. In this work, Spatial locality of input data is considered along with an efficient pre-processing method to mitigate the accuracy loss caused by the computational re-use approach. This technique was tested on LeNet and CIFAR-10 structures and was responsible for 1.9% and 1.6% accuracy loss while reducing the processing time by 38.3% and 20.9% and reducing the energy by 38.3%, and 20.7%, respectively. The models were deployed and verified on Raspberry Pi 4 B platform using the MATlab coder to measure time and energy. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Decentralized Applications in Web3: Identifying Challenges and Opportunities for Blockchain Developers

A Systematic Literature Review of Decentralized Applications...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Hossain Faruk, Md Jobair Raya, Pratusha Siam, Md Kamrul Cheng, Jerry Q. Shahriar, Hossain Cuzzocrea, Alfredo Bringas, Pablo Garcia New York Institute of Technology Department of Computer Science United States Kennesaw State University Department of Software Engineering United States University of West Florida Center for Cybersecurity United States University of Deusto D4K Group Bilbao Spain University of Calabria IDEA Lab Rende Italy University of Paris City Department of Computer Science Paris France

ISBN: (纸本)9798350362480

The Internet has opened the floor to stakeholders by redefining the way of organizing, communicating, and collaborating that was initiated by the Web's development. The advancement of the World Wide Web is an outright phenomenon and significant and we witnessed the evolution of the Web. As decentralized technologies continue to gain traction, Web3, or the decentralized internet, has emerged as a promising approach to enable a more secure, transparent, and privacy-preserved digital landscape. In this paper, we thoroughly conduct a systematic study to explore the challenges and opportunities encountered by blockchain developers in the context of decentralized applications (dApps) in Web3. We analyze a set of peer-reviewed research articles, whitepapers, and technical reports and present an in-depth understanding of the current state of Web3 development and its implications. Our finding indicates the opportunities that Web3 can facilitate, such as expanded use cases, enhanced security and privacy, decentralized infrastructure, and the potential for enabling inclusive development resources for blockchain developers. Additionally, we highlight various challenges that blockchain developers deal with including scalability, security, privacy, interoperability, and the need for standardized tools and frameworks along with various challenges in the software development lifecycle (SDLC). While there are significant challenges to overcome, the potential benefits of Web3 are substantial and could lead to a more inclusive, secure, and transparent digital ecosystem. Furthermore, we emphasize the importance of continued research, collaboration, and innovation among stakeholders to address the identified challenges and capitalize on Web3's opportunities. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE TO TARGET DISTRIBUTION VIA ASCENT REGULARIZATIONS 11

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Shuangshuang Ding, Sihao Karayiannidis, Yiannis Björkman, Mårten School of Electrical Engineering and Computer Science Royal Institute of Technology Sweden AI Lab Volvo Car Corporation Sweden Department of Automatic Control Lund University Sweden

Normalizing flows (NFs) have been shown to be advantageous in modeling complex distributions and improving sampling efficiency for unbiased *** this work, we propose a new class of continuous NFs, ascent continuous normalizing flows (ACNFs), that makes a base distribution converge faster to a target *** solving such a flow is non-trivial and barely possible, we propose a practical implementation to learn flexibly parametric ACNFs via ascent regularization and apply it in two learning cases: maximum likelihood learning for density estimation and minimizing reverse KL divergence for unbiased sampling and variational *** learned ACNFs demonstrate faster convergence towards the target distributions, therefore, achieving better density estimations, unbiased sampling and variational approximation at lower computational ***, the flows show to stabilize themselves to mitigate performance deterioration and are less sensitive to the choice of training flow length T. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

An Iterative Optimizing Framework for Radiology Report Summarization With ChatGPT

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4163-4175页

作者： Ma, Chong Wu, Zihao Wang, Jiaqi Xu, Shaochen Wei, Yaonai Liu, Zhengliang Zeng, Fang Jiang, Xi Guo, Lei Cai, Xiaoyan Zhang, Shu Zhang, Tuo Zhu, Dajiang Shen, Dinggang Liu, Tianming Li, Xiang Northwestern Polytechnical University School of Automation Xi'an710072 China University of Georgia School of Computing AthensGA30602 United States Northwestern Polytechnical University School of Computer Science Xi'an710072 China Massachusetts General Hospital Department of Radiology BostonMA02114 United States University of Electronic Science and Technology of China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China The University of Texas at Arlington Department of Computer Science and Engineering ArlingtonVA76019 United States ShanghaiTech University School of Biomedical Engineering Shanghai201210 China Shanghai United Imaging Intelligence Company Ltd. Department of Research and Development Shanghai200030 China Shanghai Clinical Research and Trial Center Shanghai201210 China

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians. Typically written by radiologists, this part is derived from the 'Findings' section, which can be laborious and error-prone. Although deep-learning-based models, such as bidirectional encoder representation from transformers (BERT), have achieved promising results in automatic impression generation (AIG), such models often require substantial amounts of medical data and have poor generalization performance. Recently, large language models (LLMs) like Chat Generative Pre-trained Transformer (ChatGPT) have shown strong generalization capabilities and performance, but their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, leveraging the contextual learning capabilities of LLMs through our dynamic prompt and iterative optimization algorithm to accomplish the AIG task. ImpressionGPT initially employs a small amount of domain-specific data to create a dynamic prompt, extracting contextual semantic information closely related to the test data. Subsequently, the iterative optimization algorithm automatically evaluates the output of LLMs and provides optimization suggestions, continuously refining the output results. The proposed ImpressionGPT model achieves superior performance of AIG task on both the Medical Information Mart for Intensive Care - Chest X-ray database (MIMIC-CXR) and Open Access Biomedical Image Search Engine (OpenI) datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Giving AI Personalities Leads to More Human-Like Reasoning

arXiv

引用

arXiv 2025年

作者： Nighojkar, Animesh Moydinboyev, Bekhzodbek Duong, My Licato, John Lab Department of Computer Science and Engineering University of South Florida TampaFL United States

In computational cognitive modeling, capturing the full spectrum of human judgment and decision-making processes, beyond just optimal behaviors, is a significant challenge. This study explores whether Large Language Models (LLMs) can emulate the breadth of human reasoning by predicting both intuitive, fast System 1 and deliberate, slow System 2 processes. Unlike traditional AI research focused on optimizing accuracy, this paper investigates the potential of AI to mimic diverse reasoning behaviors across a human population, addressing what we call the full reasoning spectrum problem. We designed reasoning tasks using a novel generalization of the Natural Language Inference (NLI) format to evaluate LLMs’ ability to replicate human reasoning. The questions were crafted to elicit both System 1 and System 2 responses. Human responses were collected through crowd-sourcing and the entire distribution was analyzed and modeled, rather than just the majority of the answers. We used personality-based prompting inspired by the Big Five personality model to elicit AI responses reflecting specific personality traits, capturing the diversity of human reasoning, and exploring how personality traits influence LLM outputs. Combined with genetic algorithms to optimize the weighting of these prompts, this method was tested alongside traditional machine learning models. The results show that LLMs can mimic human response distributions, with open-source models like Llama and Mistral unexpectedly outperforming proprietary GPT models. Personality-based prompting, especially when optimized with genetic algorithms, significantly enhanced LLMs’ ability to predict human response distributions, suggesting that capturing suboptimal, naturalistic reasoning may require modeling techniques incorporating diverse reasoning styles and psychological profiles. The study concludes that personality-based prompting combined with genetic algorithms is promising for enhancing AI’s human-ness in reasoning, pr

关键词： Genetic algorithms

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：