检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Xianzhi Zhou, Yipeng Hu, Miao Wu, Di Liao, Pengshan Guizani, Mohsen Sheng, Michael The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China The Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia The Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

To mitigate the rising concern about privacy leakage, the federated recommender (FR) paradigm emerges, in which decentralized clients co-train the recommendation model without exposing their raw user-item rating data. The differentially private federated recommender (DPFR) further enhances FR by injecting differentially private (DP) noises into clients. Yet, current DPFRs, suffering from noise distortion, cannot achieve satisfactory accuracy. Various efforts have been dedicated to improving DPFRs by adaptively allocating the privacy budget over the learning process. However, due to the intricate relation between privacy budget allocation and model accuracy, existing works are still far from maximizing DPFR accuracy. To address this challenge, we develop BGTplanner (Budget Planner) to strategically allocate the privacy budget for each round of DPFR training, improving overall training performance. Specifically, we leverage the Gaussian process regression and historical information to predict the change in recommendation accuracy with a certain allocated privacy budget. Additionally, Contextual Multi-Armed Bandit (CMAB) is harnessed to make privacy budget allocation decisions by reconciling the current improvement and long-term privacy constraints. Our extensive experimental results on real datasets demonstrate that BGTplanner achieves an average improvement of 6.76% in training performance compared to state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Mixing Histopathology Prototypes into Robust Slide-Level Representations for Cancer Subtyping

arXiv

引用

arXiv 2023年

作者： Butke, Joshua Hashimoto, Noriaki Takeuchi, Ichiro Miyoshi, Hiroaki Ohshima, Koichi Sakuma, Jun Machine Learning and Data Mining Lab University of Tsukuba Japan RIKEN Center for Advanced Intelligence Project Japan Department of Mechanical Systems Engineering Nagoya University Japan Department of Pathology Kurume University Japan Department of Computer Science Tokyo Institute of Technology Japan

Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is computationally expensive as, for each image, all instances have to be processed simultaneously. The MLP-Mixer is an under-explored alternative model to common vision transformers, especially for large-scale datasets. Due to the lack of a self-attention mechanism, they have linear computational complexity to the number of input patches but achieve comparable performance on natural image datasets. We propose a combination of feature embedding and clustering to preprocess the full whole-slide image into a reduced prototype representation which can then serve as input to a suitable MLP-Mixer architecture. Our experiments on two public benchmarks and one inhouse malignant lymphoma dataset show comparable performance to current state-of-the-art methods, while achieving lower training costs in terms of computational time and memory load. Code is publicly available at https://***/butkej/ProtoMixer. Copyright © 2023, The Authors. All rights reserved.

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

Research Highlights (Required) to Create Your Highlights, Please Type the Highlights Against Each /Item Command. /Item Address the Question "When to Adapt" Which is Ignored by Prior Works /Item Show a Correlation between Domain Gap and Detection Accuracy /Item Show Domain Gap Can Help Save Up to About 90% of Total Energy Usage for Continual Domain Adaption Without Sacrificing the Overall Performance of Object Detectors

SSRN

引用

SSRN 2023年

作者： Doan, Anh-Dzung Nguyen, Bach Long Gupta, Surabhi Reid, Ian Wagner, Markus Chin, Tat-Jun Australian Institute for Machine Learning The University of Adelaide AdelaideSA5000 Australia Department of Data Science and Artificial Intelligence Monash University MelbourneVIC3800 Australia Safran Electronics & Defense Australasia BotanyNSW2019 Australia

To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons. Continually adapting the detector to incorporate these changes is a promising solution, but it can be computationally costly. Our proposed approach is to selectively adapt the detector only when necessary, using new data that does not have the same distribution as the current training data. To this end, we investigate three popular metrics for domain gap evaluation and find that there is a correlation between the domain gap and detection accuracy. Therefore, we apply the domain gap as a criterion to decide when to adapt the detector. Our experiments show that our approach has the potential to improve the efficiency of the detector’s operation in real-world scenarios, where environmental conditions change in a cyclical manner, without sacrificing the overall performance of the detector. Our code is publicly available https://***/dadung/DGE-CDA. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Assessing Domain Gap for Continual Domain Adaptation in Object Detection

arXiv

引用

arXiv 2023年

To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons. Continually adapting the detector to incorporate these changes is a promising solution, but it can be computationally costly. Our proposed approach is to selectively adapt the detector only when necessary, using new data that does not have the same distribution as the current training data. To this end, we investigate three popular metrics for domain gap evaluation and find that there is a correlation between the domain gap and detection accuracy. Therefore, we apply the domain gap as a criterion to decide when to adapt the detector. Our experiments show that our approach has the potential to improve the efficiency of the detector's operation in real-world scenarios, where environmental conditions change in a cyclical manner, without sacrificing the overall performance of the detector. Our code is publicly available https://***/dadung/DGE-CDA. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation-Based Deep learning Models for Forecasting and Diagnosis of Glaucoma Disease

TechRxiv

引用

TechRxiv 2022年

作者： Madadi, Yeganeh Abu-Serhan, Hashem Yousefi, Siamak The Data Mining and Machine Learning Laboratory Department of Ophthalmology University of Tennessee Health Science Center TN United States The Hamad Medical Corporation QA Doha Qatar

Domain adaptation methods are designed to extract shared domain-invariant features by projecting data on a common subspace in order to align their domain distributions. However, these methods do not usually consider domain-specific features, and therefore their distributions may not be well aligned. To address this problem, we introduce a novel model that learns domain-invariant and domain-specific representations to extract both their general and specific features. We also propose progressive weighting to accurately transfer the source domain knowledge and to mitigate negative knowledge transfer from the source to the target domain and to employ low-rank coding for aligning the source and target distributions. We evaluated the model based on several real-world datasets and showed that our method significantly improved the accuracy for forecasting and diagnosis of glaucoma disease from fundus photographs. © 2022-10-25, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

SPEAR: Design and Implementation of an Advanced Virtual Assistant

SPEAR: Design and Implementation of an Advanced Virtual Assi...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Garima Jain Amita Shukla Nitesh Kumar Bairwa Anamika Chaudhary Ashish Patel Ankush Jain Department of Computer Science and Buisness Systems Noida Institute of Engineering and Technology Greater Noida India Department of Artificial Intelligence Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Greater Noida India Department of Artificial Intelligence and Machine Learning Dronacharya Group of Institutions Greater Noida India Department of Computer Science and Enginnering Netaji Subhash University of Technology Delhi India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

This research presents the development and evaluation of SPEAR, an advanced voice-activated personal desktop assistant designed to address challenges in existing virtual assistant technology, such as limited language support, low recognition accuracy, and inadequate task automation. Despite recent advancements in Natural Language Processing (NLP) and machine learning, implementation in current systems remains subpar. SPEAR achieves an 88% overall command execution success rate, with a speech recognition accuracy of 92% and an average response time of 1.8 seconds, demonstrating efficiency in real-time interactions. Developed using Python and machine learning libraries, SPEAR supports 15 voice commands across multiple platforms, excelling in note creation (95% success), web searching (94%), and information retrieval (92%). Its natural language understanding score of 0.86 and context retention rate of 75% highlight its conversational capabilities. While the assistant performs well in messaging functionality (85% success) and currently supports three languages, expanding its multilingual capabilities is essential for broader user engagement. Metrics indicate a satisfaction score of 8.2/10 and an average of 12 daily interactions per user, showcasing its practical utility. Additionally, the system's text-to-speech quality (8.5/10) and error recovery rate (82 %) affirm its robustness. These findings contribute valuable insights for future research, focusing on enhancing multilingual support, broadening task categories, and improving context retention, ultimately positioning SPEAR to rival established industry leaders by offering a comprehensive suite of services.

关键词： Accuracy Personal voice assistants machine learning Information retrieval Natural language processing Real-time systems Robustness Text to speech Time factors Web search

来源：评论

学校读者我要写书评

暂无评论

SpectralNET: Exploring spatial-spectral WaveletCNN for hyperspectral image classification

arXiv

引用

arXiv 2021年

作者： Chakraborty, Tanmay Trehan, Utkarsh Zuluaga, Maria A. MALIS - Machine Learning and Intelligent Systems Department of Data Science and Engineering EURECOM Biot France

Hyperspectral Image (HSI) classification using Convolutional Neural Networks (CNN) is widely found in the current literature. Approaches vary from using SVMs to 2D CNNs, 3D CNNs, 3D-2D CNNs. Besides 3D-2D CNNs and FuSENet, the other approaches do not consider both the spectral and spatial features together for HSI classification task, thereby resulting in poor performances. 3D CNNs are computationally heavy and are not widely used, while 2D CNNs do not consider multi-resolution processing of images, and only limits itself to the spatial features. Even though 3D-2D CNNs try to model the spectral and spatial features their performance seems limited when applied over multiple dataset. In this article, we propose SpectralNET, a wavelet CNN, which is a variation of 2D CNN for multi-resolution HSI classification. A wavelet CNN uses layers of wavelet transform to bring out spectral features. Computing a wavelet transform is lighter than computing 3D CNN. The spectral features extracted are then connected to the 2D CNN which bring out the spatial features, thereby creating a spatial-spectral feature vector for classification. Overall a better model is achieved that can classify multi-resolution HSI data with high accuracy. Experiments performed with SpectralNET on benchmark dataset, i.e. Indian Pines, University of Pavia, and Salinas Scenes confirm the superiority of proposed SpectralNET with respect to the state-of-the-art methods. The code is publicly available in https://***/tanmay-ty/SpectralNET. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Pattern Discovery in an EEG database of Depression Patients: Preliminary Results

Pattern Discovery in an EEG Database of Depression Patients:...

引用

International Conference on Measurement

作者： Kateřina Hlaváčková-Schindler Christina Pacher Claudia Plant Mykola Lazarenko Milan Paluš Jaroslav Hlinka Aditi Kathpalia Martin Brunovský Data Mining and Machine Learning Research Group Faculty of Computer Science University of Vienna Vienna Austria Department of Complex Systems Institute of Computer Science Czech Academy of Sciences Prague Czechia Clinical Research Programme National Institute of Mental Health Klecany Czechia

The ability to predict response to medication treatment of depressed patients, either early in the course of therapy or before treatment even begins can avoid trials of ineffective therapy and save patients from prolonged intervals of suffering. Symptom alleviation requires 4-6 weeks after starting current antidepressive medication. Based on the data basis of the patients and their EEG before and on the 7th day of treatment we apply data mining, causal discovery and machine learning approaches to discover interactive patterns between patient’s brain regions to separate the treatment responders from non-responders. In this paper we report the preliminary results of our international project "learning Synchronization Patterns in Multivariate Neural Signals for Prediction of Response to Antidepressants" ongoing at the University of Vienna, the Czech Academy of sciences and the National Institute of Mental Health in the Czech Republic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empowering LLMs with Logical Reasoning: A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Cheng, Fengxiang Li, Haoxuan Liu, Fenrong van Rooij, Robert Zhang, Kun Lin, Zhouchen Institute for Logic Language and Computation University of Amsterdam Netherlands Center for Data Science Peking University China Machine Learning Department MBZUAI Department of Philosophy Tsinghua University China Department of Philosophy CMU United States Institute for Artificial Intelligence Peking University China Peng Cheng Laboratory China National Key Lab of General AI School of Intelligence Science and Technology Peking University China

Large language models (LLMs) have achieved remarkable successes on various natural language tasks. However, recent studies have found that there are still significant challenges to the logical reasoning abilities of LLMs. This paper summarizes and categorizes the main challenges into two aspects: (1) Logical question answering, LLMs often fail to generate the correct answer within complex logical problem which requires sophisticated deductive, inductive or abductive reasoning given a collection of premises and constrains. (2) Logical consistency, LLMs are prone to producing responses contradicting themselves across different questions. For example, a state-of-the-art Macaw question-answering LLM answers Yes to both questions Is a magpie a bird? and Does a bird have wings? but answers No to Does a magpie have wings?. To facilitate this research direction, we comprehensively investigate the most cutting-edge methods and propose detailed taxonomies of these methods. Specifically, to accurately answer complex logic questions, previous methods can be categorized based on reliance on external solvers, prompts, pretraining, and fine-tuning. To avoid logical contradictions, we discuss concepts and solutions of various logical consistencies, including implication, negation, transitivity, factuality consistency, and their composites. In addition, we review commonly used benchmark datasets and evaluation metrics, and discuss promising research directions, such as extensions to modal logic to account for uncertainty, and efficient algorithms satisfying multiple logical consistencies simultaneously. © 2025, CC BY.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Analyzing Atomic Interactions in Molecules as Learned by Neural Networks

arXiv

引用

arXiv 2024年

作者： Esders, Malte Schnake, Thomas Lederer, Jonas Kabylda, Adil Montavon, Grégoire Tkatchenko, Alexandre Müller, Klaus-Robert BIFOLD Berlin Institute for the Foundations of Learning and Data Germany Machine Learning Group Berlin Institute of Technology Berlin10587 Germany Department of Physics and Materials Science University of Luxembourg Luxembourg CityL-1511 Luxembourg Department of Mathematics and Computer Science Free University of Berlin Germany Google Deepmind Berlin Germany Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Max Planck Institute for Informatics Saarbrücken66123 Germany

While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a test set alone is not a guarantee for robust chemical modeling such as stable molecular dynamics (MD). To go beyond accuracy, we use explainable artificial intelligence (XAI) techniques to develop a general analysis framework for atomic interactions and apply it to the SchNet and PaiNN neural network models. We compare these interactions with a set of fundamental chemical principles to understand how well the models have learned the underlying physicochemical concepts from the data. We focus on the strength of the interactions for different atomic species, how predictions for intensive and extensive quantum molecular properties are made, and analyze the decay and many-body nature of the interactions with interatomic distance. Models that deviate too far from known physical principles produce unstable MD trajectories, even when they have very high energy and force prediction accuracy. We also suggest further improvements to the ML architectures to better account for the polynomial decay of atomic interactions. Copyright © 2024, The Authors. All rights reserved.

关键词： Molecular dynamics

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：