检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Tianyu Chen Kevin Bello Francesco Locatello Bryon Aragam Pradeep Ravikumar Department of Statistics and Data Sciences University of Texas at Austin Booth School of Business University of Chicago and Machine Learning Department Carnegie Mellon University Institute of Science and Technology Austria Booth School of Business University of Chicago Machine Learning Department Carnegie Mellon University

ISBN: (纸本)9798331314385

We consider the linear causal representation learning setting where we observe a linear mixing of d unknown latent factors, which follow a linear structural causal model. Recent work has shown that it is possible to recover the latent factors as well as the underlying structural causal model over them, up to permutation and scaling, provided that we have at least d environments, each of which corresponds to perfect interventions on a single latent node (factor). After this powerful result, a key open problem faced by the community has been to relax these conditions: allow for coarser than perfect single-node interventions, and allow for fewer than d of them, since the number of latent factors d could be very large. In this work, we consider precisely such a setting, where we allow a smaller than d number of environments, and also allow for very coarse interventions that can very coarsely change the entire causal graph over the latent factors. On the flip side, we relax what we wish to extract to simply the list of nodes that have shifted between one or more environments. We provide a surprising identifiability result that it is indeed possible, under some very mild standard assumptions, to identify the set of shifted nodes. Our identifiability proof moreover is a constructive one: we explicitly provide necessary and sufficient conditions for a node to be a shifted node, and show that we can check these conditions given observed data. Our algorithm lends itself very naturally to the sample setting where instead of just interventional distributions, we are provided datasets of samples from each of these distributions. We corroborate our results on both synthetic experiments as well as an interesting psychometric dataset. The code can be found at https://***/TianyuCodings/iLCS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving the Quality of Diabetic data with Large Language Model-driven Cleaning Techniques

Improving the Quality of Diabetic Data with Large Language M...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Biradar, Divya Dattangire, Rahul Vaidya, Ruchika Inti, NagaSuryaShivani University of Texas at Arlington Computer Science ArlingtonTX76013 United States Data Engineering HoustonTX77002 United States Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Maharashtra Wardha442001 India University of Texas at Arlington Computer and Information Science ArlingtonTX76013 United States

ISBN: (纸本)9798331539948

The data-cleaning approach applies the capabilities of large language models to reduce the noise in the extracted and received data from healthcare sources. The aim will be to clean the collected and extracted data by looking up and dealing with the inaccuracies encountered during the project like missing or duplicated records, outliers, and data that will not add any value to the project. The 'Diabetes' data set from Kaggle is divided into implementing the combined approach data-cleaning process such as removing duplicate entries, and emptying fields by a Large Language Model, to improve the accuracy is assessed. Three components will increase the reliability of the collected data: 1. Gateway, 2. Storage 3. Cleaning. The outcomes demonstrated the LLMbased approach's effective impact in correcting and consistent data within the healthcare dataset. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Robust Universal Inference

arXiv

引用

arXiv 2023年

作者： Park, Beomjo Balakrishnan, Sivaraman Wasserman, Larry Department of Statistics & Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States

In statistical inference, it is rarely realistic that the hypothesized statistical model is well-specified, and consequently it is important to understand the effects of misspecification on inferential procedures. When the hypothesized statistical model is misspecified, the natural target of inference is a projection of the data generating distribution onto the model. We present a general method for constructing valid confidence sets for such projections, under weak regularity conditions, despite possible model misspecification. Our method builds upon the universal inference method of Wasserman et al. [41] and is based on inverting a family of split-sample tests of relative fit. We study settings in which our methods yield either exact or approximate, finite-sample valid confidence sets for various projection distributions. We study rates at which the resulting confidence sets shrink around the target of inference and complement these results with a simulation study. Copyright © 2023, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

On the origins of linear representations in large language models 24

On the origins of linear representations in large language m...

引用

Proceedings of the 41st International Conference on machine learning

作者： Yibo Jiang Goutham Rajendran Pradeep Ravikumar Bryon Aragam Victor Veitch Department of Computer Science University of Chicago Machine Learning Department Carnegie Mellon University Booth School of Business University of Chicago Department of Statistics and Data Science Institute University of Chicago

Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple latent variable model to abstract and formalize the concept dynamics of the next token prediction. We use this formalism to show that the next token prediction objective (softmax with cross-entropy) and the implicit bias of gradient descent together promote the linear representation of concepts. Experiments show that linear representations emerge when learning from data matching the latent variable model, confirming that this simple structure already suffices to yield linear representations. We additionally confirm some predictions of the theory using the LLaMA-2 large language model, giving evidence that the simplified model yields generalizable insights.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thai Conversational Chatbot Classification Using BiLSTM and data Augmentation 1st

Thai Conversational Chatbot Classification Using BiLSTM and ...

引用

1st International Conference on data science and Artificial Intelligence, DSAI 2023

作者： Lhasiw, Nunthawat Tanantong, Tanatorn Sanglerdsinlapachai, Nuttapong Thammasat Research Unit in Data Innovation and Artificial Intelligence Department of Computer Science Faculty of Science and Technology Thammasat University Pathum Thani Thailand Strategic Analytics Networks with Machine Learning and AI Research Team National Electronics and Computer Technology Center Pathum Thani Thailand

ISBN: (纸本)9789819979684

Chatbot platforms, e.g., Facebook and Line, have revolutionized human interaction in the digital age. In order to develop an automatic chatbot classification, there are several challenges especially for Thai chat messages. Conversational messages are usually short and ambiguous. Therefore, it is difficult to find a dataset for constructing an effective classification model. To address the limited size of the dataset, data augmentation techniques can be possibly applied. data augmentation involves generating synthetic messages by applying various transformations to existing data samples while preserving their original meaning. In this study, the size and diversity of the dataset is increased by two methods, i.e., text augmentation using word2vec from Thai2Fit and English-Thai machine translation models proposed by VISTEC. Based on the augmented messages, a Deep learning technique, BiLSTM, is used to construct a chatbot classification model. The experimental obtained results demonstrate that data augmentation can help to increase the classification performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Protocon: Pseudo-Label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-Supervised learning

Protocon: Pseudo-Label Refinement via Online Clustering and ...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Islam Nassar Munawar Hayat Ehsan Abbasnejad Hamid Rezatofighi Gholamreza Haffari Data Science and AI Department Monash University Australia Australian Institute for Machine Learning The University of Adelaide Australia

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose Protocon, a novel SSL method aimed at the less-explored label-scarce SSL where such methods usually underperform. Protocon refines the pseudolabels by lever-aging their nearest neighbours' information. The neighbours are identified as the training proceeds using an online clustering approach operating in an embedding space trained via a prototypical loss to encourage well-formed clusters. The online nature of Protocon allows it to utilise the label history of the entire dataset in one training cycle to refine labels in the following cycle without the need to store image embeddings. Hence, it can seamlessly scale to larger datasets at a low cost. Finally, Protocon addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss. It delivers significant gains and faster convergence over state-of-the-art across 5 datasets, including CIFARs, ImageNet and DomainNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distance-Preserving Spatial Representations in Genomic data

arXiv

引用

arXiv 2024年

作者： Zhou, Wenbin Du, Jin-Hong Heinz College of Information Systems and Public Policy Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics and Data Science Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States

The spatial context of single-cell gene expression data is crucial for many downstream analyses, yet often remains inaccessible due to practical and technical limitations, restricting the utility of such datasets. In this paper, we propose a generic representation learning and transfer learning framework dp-VAE, capable of reconstructing the spatial coordinates associated with the provided gene expression data. Central to our approach is a distance-preserving regularizer integrated into the loss function during training, ensuring the model effectively captures and utilizes spatial context signals from reference datasets. During the inference stage, the produced latent representation of the model can be used to reconstruct or impute the spatial context of the provided gene expression by solving a constrained optimization problem. We also explore the theoretical connections between distance-preserving loss, distortion, and the bi-Lipschitz condition within generative models. Finally, we demonstrate the effectiveness of dp-VAE in different tasks involving training robustness, out-of-sample evaluation, and transfer learning inference applications by testing it over 27 publicly available datasets. This underscores its applicability to a wide range of genomics studies that were previously hindered by the absence of spatial data. © 2024, CC BY.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

PROTOCON: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised learning

arXiv

引用

arXiv 2023年

作者： Nassar, Islam Hayat, Munawar Abbasnejad, Ehsan Rezatofighi, Hamid Haffari, Gholamreza Data Science and AI Department Monash University Australia Australian Institute for Machine Learning The University of Adelaide Australia

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose PROTOCON, a novel SSL method aimed at the less-explored label-scarce SSL where such methods usually underperform. PROTOCON refines the pseudo-labels by leveraging their nearest neighbours' information. The neighbours are identified as the training proceeds using an online clustering approach operating in an embedding space trained via a prototypical loss to encourage well-formed clusters. The online nature of PROTOCON allows it to utilise the label history of the entire dataset in one training cycle to refine labels in the following cycle without the need to store image embeddings. Hence, it can seamlessly scale to larger datasets at a low cost. Finally, PROTOCON addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss. It delivers significant gains and faster convergence over state-of-the-art across 5 datasets, including CIFARs, ImageNet and DomainNet. © 2023, CC BY-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Dynamic Channel Allocation Using Reinforcement learning Algorithm for Multiple Input Multiple Output Systems 3

Dynamic Channel Allocation Using Reinforcement Learning Algo...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Bittla, Srinivasa Rao Riadhusin, Raami Divyaraj, G.N. Aravindh, S. Ahila, B. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering chennai India Dhanalakshmi Srinivasan College of Engineering Technology Department of Artificial Intelligence and Data Science Mamallapuram India

ISBN: (纸本)9798331508456

In recent years, Multiple-Input Multiple-Output systems (MIMO) play a crucial role in modern wireless networks by enhancing spectral efficiency and data rates. Traditional static, heuristic-based allocation methods struggled to adapt to real-time variations, handling high-dimensional state spaces, minimizing interference, and ensuring fairness in channel allocation. However, decision-making in dynamic environments requires intelligent and scalable approach that enables real-time decision-making by efficiently learning and adapting to changing network conditions. To overcome these issues. This research proposed Deep Q-Network with Prioritized Experience Replay (DQN-PER) for dynamic channel allocation for MIMO Systems. DQN-PER prioritizes high-value learning experiences and while also improving training efficiency and convergence speed. PER prioritizes important experiences based on Temporal-Difference (TD) error by allowing the model to focus on more informative transitions, which speeds up learning and improves adaptability. Simulation results demonstrate enhanced spectral efficiency, reduced packet loss, and improved Quality of Service (QoS) in dynamic wireless environments. These findings establish DQN-PER as a promising solution for intelligent and adaptive MIMO resource allocation. The proposed method achieved better results in terms of a packet drop rate 0.04 compared to existing method Advantage Actor-Critic (A2C). © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Prevent data in Embedded Based Customized Wireless Message Transmitting System Using AES Algorithm with Artificial Bee Colony Optimisation Techniques 1

Prevent Data in Embedded Based Customized Wireless Message T...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Sathia Priya, M. Bhagavathi Priya, M. Manojkumar, B. Vijayakumar, M. Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Dr.Mahalingam College of Engineering & Technology Department of Artificial Intelligence & Machine Learning Pollachi India Dr. Mahalingam College of Engineering & Technology Department of Artificial Intelligence & Data Science Pollachi India

ISBN: (纸本)9798350359756

The sender encrypts a message before transferring it to the recipient over a channel in a unidirectional, linear process, according to the transmission model of communication. Hardware and software components known as "message transmission systems"are in charge of managing the transmission path and the communication process. It is possible to study transmission data with the traditional information theory, which is based on "emitters,""messages,"and "receivers". The execution of control tasks such data collecting, control algorithm execution, system identification, and actuation frequently takes place in several system nodes. The effectiveness of a status monitoring system where a sensor delivers sporadic status updates to a remote monitor across a network is observed. Additionally, wireless protocol is utilized in embedded devices to convey messages because it is made for lightweight devices and unstable network conditions. The core concept is to develop a new class of applications through direct interaction amongst intelligent techniques, without the requirement for human involvement. Because it embeds user personal data and activates the aims of information, data prevention is crucial for information sharing. This article has covered the issues of using wireless data, messages, or information with an encryption system, as well as a summary of previous studies in the field. A suggested plan of action has also been offered. To protect user data and privacy safer than any other existing approach, the proposed system also uses Artificial Bee Colony Optimisation (ABC) to optimise the key used for encrypting the sensor data with the aid of the AES Encryption algorithm. Even so, the suggested solution uses less time to encrypt and decode patent data before saving it to the server. © 2023 IEEE.

关键词： Information theory

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：