检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Cuong Pham Cuong C. Nguyen Trung Le Dinh Phung Gustavo Carneiro Thanh-Toan Do Department of Data Science and AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia Department of Data Science and AI Monash University Australia and VinAI Vietnam Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Bayesian Neural Networks (BNNs) offer probability distributions for model parameters, enabling uncertainty quantification in predictions. However, they often underperform compared to deterministic neural networks. Utilizing mutual learning can effectively enhance the performance of peer BNNs. In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning. The proposed approaches aim to increase diversity in both network parameter distributions and feature distributions, promoting peer networks to acquire distinct features that capture different characteristics of the input, which enhances the effectiveness of mutual learning. Experimental results demonstrate significant improvements in the classification accuracy, negative log-likelihood, and expected calibration error when compared to traditional mutual learning for BNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

No Rose for MLE: Inadmissibility of MLE for Evaluation Aggregation Under Levels of Expertise

No Rose for MLE: Inadmissibility of MLE for Evaluation Aggre...

引用

IEEE International Symposium on Information Theory

作者： Charvi Rastogi Ivan Stelmakh Nihar Shah Sivaraman Balakrishnan Machine Learning Department Carnegie Mellon University Computer Science Department Carnegie Mellon University Department of Statistics and Data Science Carnegie Mellon University

ISBN: (数字)9781665421591

ISBN: (纸本)9781665421607

A number of applications including crowd-sourced labeling and peer review require aggregation of labels or evaluations sourced from multiple evaluators. There is often additional information available pertaining to the evaluators’ expertise. A natural approach for aggregation is to consider the widely studied Dawid-Skene model (or its extensions incorporating evaluators’ expertise), and employ the standard maximum likelihood estimator (MLE). While MLE is in general widely used in practice and enjoys a number of appealing theoretical guarantees, in this work we provide a negative result for the MLE. Specifically, we prove that the MLE is asymptotically inadmissible for a special case of evaluation aggregation with expertise level information. We show this by constructing an alternative estimator that we show is significantly better than the MLE in certain parameter regimes and at least as good elsewhere. Finally, simulations reveal that our findings may hold in more general conditions than what we theoretically analyze.

关键词： Maximum likelihood estimation Analytical models Labeling Standards Information theory

来源：评论

学校读者我要写书评

暂无评论

Method for Finding an Investment Strategy in the Case of a Sparse Covariance Matrix

Method for Finding an Investment Strategy in the Case of a S...

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Victor Gorelik Tatiana Zolotova Department of Simulation Systems and Operations Research Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences Moscow Russia Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow Russia

An optimality principle is proposed for making investment decisions based on efficiency and risk assessments with a sparse covariance matrix. The method is implemented as a program with a graphical interface and demon... 详细信息

ISBN: (数字)9798350375718

ISBN: (纸本)9798350375725

关键词： Large-scale systems Sparse matrices Risk management Covariance matrices Stock markets Portfolios Investment

来源：评论

学校读者我要写书评

暂无评论

Application of Deep learning Methods for Forest Fire Intelligent Image Processing 2nd

Application of Deep Learning Methods for Forest Fire Intelli...

引用

2nd International Conference on Advances in Information and Communication Technology, ICTA 2023

作者： Long, Nguyen The Huong, Nguyen Thu G, Shmeleva Anna. Lien, Pham Thi Department of Informatics Institute of Cybersecurity and Digital Technologies MIREA – Russian Technological University Moscow119454 Russia Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk664074 Russia University of Information and Communication Technology Thai Nguyen University Thai Nguyen70000 Viet Nam

ISBN: (纸本)9783031495281

There are many challenges for a Deep learning application project. Many problems need to be solved in an optimal way to improve the performance of the system. We can focus on a specific step or on the whole process. The aim of the work is to show a new way of using convolutional neural networks is proposed to image intelligent process. Due to the influence of climate change, natural disasters are becoming more complicated and have serious consequences. In particular, the phenomenon of forest fires is affected by factors such as humidity, temperature and vegetation characteristics, etc., so the detection and prediction of forest fires face many challenges. In this study, we focus on using image processing techniques and visual algorithms to preprocess data and filter noise, in order to create a complete database for training and testing model. Natural elements are also used in combination with object features (forest fire images) to build feature vectors. This study will allow to develop the technology and open up new opportunities for its subsequent application. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Yield Predictions with Real-Time IoT Sensor data and machine learning Integration

Enhancing Agricultural Yield Predictions with Real-Time IoT ...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Chandiraprakash. N A. Chinnasamy M Ashok Department of Artificial intelligence and machine learning Malla Reddy College of Engineering Hyderabad India Department of Data Science and Business Systems school of computing SRMIST kattankulathur campus Chennai India Malla Reddy College of Engineering Hyderabad India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

This research extends previous studies on the effects of climate change on agricultural yield predictions by integrating advanced machine learning (ML) methods with real time environmental sensing data. It builds on the basic usage of Long Short-Term Memory (LSTM) and Random Forest (RF) methods by employing real time data streams from IoT based field sensors that measure soil moisture, nutrient levels and pest activity. The aim is to enhance the prediction model's adaption to changing climatic circumstances, therefore increasing their utility in agricultural management. This study proposes a dynamic adaptation feature that uses real time data to make timely adjustments to crop management predictions. Moreover, the integration of Convolutional Neural Network (CNN) with LSTM is being investigated to increase the spatial and temporal accuracy of these predictions. By integrating conventional climatic data with detailed micro environmental elements from IoT sensors, this method obtains a aspects which affects the crop growth. This study also focuses on developing a userfriendly interface that allows farmers to easily access predictive developments and recommendations, allowing for more informed decision making. This technique is predicted to make substantial advances in precision agriculture, giving more effective methods for regulating agricultural productivity in dynamic climatic variability. These results may improve food security and sustainability by optimizing resource utilization and reducing the environmental impact of farming operations.

关键词： Precision agriculture Accuracy Decision making Crops Predictive models Real-time systems Sensors Convolutional neural networks Long short term memory Farming

来源：评论

学校读者我要写书评

暂无评论

A machine learning and Explainable AI Framework Tailored for Unbalanced Experimental Catalyst Discovery

arXiv

引用

arXiv 2024年

作者： Semnani, Parastoo Bogojeski, Mihail Bley, Florian Zhang, Zizheng Wu, Qiong Kneib, Thomas Herrmann, Jan Weisser, Christoph Patcas, Florina Müller, Klaus-Robert Machine Learning Group TU Berlin Berlin Germany Berlin Institute for the Foundations of Learning and Data Berlin Germany BASLEARN-TU Berlin BASF Joint Lab for Machine Learning TU Berlin Berlin Germany Georg-August-University Göttingen Statistics and Campus Institute Data Science Göttingen Germany BASF SE Ludwigshafen Germany Max Planck Institute for Informatics Saarbrücken Germany Department of Artificial Intelligence Korea University Seoul Korea Republic of

The successful application of machine learning in catalyst design depends on high-quality and diverse data to ensure effective generalization to novel compositions, thereby aiding in catalyst discovery. However, due to the complex interactions of catalyst components, the design of novel catalysts has long relied on trial-and-error, a costly and labor-intensive process that results in scarce data that is heavily biased towards undesired, low-yield catalysts. Despite the increasing popularity of machine learning applications in this field, most of the efforts so far have not focused on dealing with the challenges presented by such experimental data. To address these challenges, we introduce a robust machine learning and explainable AI framework to accurately classify the catalytic yield of various compositions and identify the contributions of individual components to the yield. This framework combines a series of ML practices designed to handle the scarcity and imbalance of catalyst data. We apply the framework to the task of determining the yield of different catalyst combinations in oxidative methane coupling, and use it to evaluate the performance of a range of ML models: tree-based models (such as decision trees, random forest, and gradient boosted trees), logistic regression, support vector machines, and neural networks. These experiments demonstrate that the methods used in our framework lead to a significant improvement in the performance of all but one of the evaluated models. Additionally, the decision-making process of each ML model is analyzed by identifying the most important features for predicting catalyst performance using explainable AI (XAI) methods. Our analysis found that XAI methods, which provide class-aware explanations, such as Layer-wise Relevance Propagation, managed to identify key components that contribute specifically to high-yield catalysts. These findings align with chemical intuition and existing literature, reinforcing their validity.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Vector databases and Vector Embeddings-Review

Vector Databases and Vector Embeddings-Review

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Kukreja, Sanjay Kumar, Tarun Bharate, Vishal Purohit, Amit Dasgupta, Abhijit Guha, Debashis Sp Jain School of Global Management Department of Machine Learning Mumbai India EClerx Services Ltd. Coe AI-ML Chandigarh India EClerx Services Ltd. Coe AI-ML Pune India EClerx Services Ltd. Coe AI-ML Mumbai India Sp Jain School of Global Management Department of Data Science Mumbai India

ISBN: (纸本)9798350382914

This research paper aims to present a comprehensive survey of vector databases and vector embedding techniques. A concise overview of the evolution, architecture, advantages and challenges of vector databases are presented in this paper. To convert unstructured data into vectors, various embedding techniques with their in-depth technical description are also surveyed in this research paper. The existing vector databases' characteristics and features are described to select an appropriate vector database. The embedding and indexing techniques are thoroughly discussed to help the research community experiment with combining them to develop their application. The challenges of vector databases, like selecting distance metrics, dimensionality, data integrity, cost, etc. are presented. This information on vector database systems will help researchers to exhibit further advancements in their data science applications. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

CROSS-TECHNOLOGY GENERALIZATION IN SYNTHESIZED SPEECH DETECTION: EVALUATING AST MODELS WITH MODERN VOICE GENERATORS

arXiv

引用

arXiv 2025年

作者： Ustinov, Andrew Yordanov, Matey Kuchma, Andrei Bychkov, Mikhail Department of Machine Learning and Data Analytics ITMO University Russia AI Innovation Hub ANTEI Limited Hong Kong Department of Integrative Systems and Design Hong Kong University of Science and Technology AI Innovation Hub ANTEI Limited Hong Kong

This paper evaluates the Audio Spectrogram Transformer (AST) architecture for synthesized speech detection, with focus on generalization across modern voice generation technologies. Using differentiated augmentation strategies, the model achieves 0.91% EER overall when tested against ElevenLabs, NotebookLM, and Minimax AI voice generators. Notably, after training with only 102 samples from a single technology, the model demonstrates strong cross-technology generalization, achieving 3.3% EER on completely unseen voice generators. This work establishes benchmarks for rapid adaptation to emerging synthesis technologies and provides evidence that transformer-based architectures can identify common artifacts across different neural voice synthesis methods, contributing to more robust speech verification systems. © 2025, CC BY-NC-ND.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity

arXiv

引用

arXiv 2024年

作者： Lin, Zhanran Li, Puheng Wu, Lei Department of Statistics and Data Science Wharton School University of Pennsylvania United States Department of Statistics Stanford University United States School of Mathematical Sciences Peking University China Center for Machine Learning Research Peking University China

One of the most intriguing findings in the structure of neural network landscape is the phenomenon of mode connectivity [FB17, DVSH18]: For two typical global minima, there exists a path connecting them without barrier. This concept of mode connectivity has played a crucial role in understanding important phenomena in deep learning. In this paper, we conduct a fine-grained analysis of this connectivity phenomenon. First, we demonstrate that in the overparameterized case, the connecting path can be as simple as a two-piece linear path, and the path length can be nearly equal to the Euclidean distance. This finding suggests that the landscape should be nearly convex in a certain sense. Second, we uncover a surprising star-shaped connectivity: For a finite number of typical minima, there exists a center on minima manifold that connects all of them simultaneously via linear paths. These results are provably valid for linear networks and two-layer ReLU networks under a teacher-student setup, and are empirically supported by models trained on MNIST and CIFAR-10. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improved Approach for Mapping Anthropological Facial Features Based on A Convolutional Neural Network 2nd

Improved Approach for Mapping Anthropological Facial Feature...

引用

2nd International Conference on Advances in Information and Communication Technology, ICTA 2023

作者： Huong, Nguyen Thu Long, Nguyen The Lien, Pham Thi Department of Informatics Institute of Cybersecurity and Digital Technologies MIREA – Russian Technological University Moscow119454 Russia Laboratory of Artificial Intelligence and Machine Learning Institute of Information Technology and Data Science Irkutsk National Research Technical University Irkutsk664074 Russia University of Information and Communication Technology Thai Nguyen University Thai Nguyen70000 Viet Nam

ISBN: (纸本)9783031495281

Our facial anthropological and actions are non-verbal communication tools that account for 93% of emotions in human communication, 55% of which are facial expressions and gestures. Facial emotions can be easily analyzed from facial images, and computers can interact with people the way people interact with each other. For this reason, automatic classification and analysis of facial emotions is currently an interesting and challenging problem that has great implications for society. In this work, the random forest method combined with a neural network was proposed to improve the classification of emotions by building feature maps. Training and testing models were built to perform the experiments, which achieved very good accuracy in the range of 98.5% to 99.7% for the two datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

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：