检索结果-内蒙古大学图书馆

Explainable Differential Privacy-hyperdimensional computing for Balancing Privacy and Transparency in Additive Manufacturing Monitoring

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 147卷

作者： Piran, Fardin Jalil Poduval, Prathyush P. Barkam, Hamza Errahmouni Imani, Mohsen Imani, Farhad Univ Connecticut Sch Mech Aerosp & Mfg Engn Storrs CT 06269 USA Univ Calif Irvine Dept Comp Sci Irvine CA 92697 USA

Machine Learning (ML) models integrated with in-situ sensing offer transformative solutions for defect detection in Additive Manufacturing (AM), but this integration brings critical challenges in safeguarding sensitive data, such as part designs and material compositions. Differential Privacy (DP), which introduces mathematically controlled noise, provides a balance between data utility and privacy. However, black-box Artificial Intelligence (AI) models often obscure how this noise impacts model accuracy, complicating the optimization of privacy-accuracy trade-offs. This study introduces the Differential Privacy-hyperdimensional computing (DP-HD) framework, a novel approach combining Explainable AI (XAI) and vector symbolic paradigms to quantify and predict noise effects on accuracy using a Signal-to-Noise Ratio (SNR) metric. DP-HD enables precise tuning of DP noise levels, ensuring an optimal balance between privacy and performance. The framework has been validated using real-world AM data, demonstrating its applicability to industrial environments. Experimental results demonstrate DP-HD's capability to achieve state-of-the-art accuracy (94.43%) with robust privacy protections in anomaly detection for AM, even under significant noise conditions. Beyond AM, DP-HD holds substantial promise for broader applications in privacy-sensitive domains such as healthcare, financial services, and government data management, where securing sensitive data while maintaining high ML performance is paramount.

关键词： Explainable Artificial Intelligence hyperdimensional computing Differential Privacy Additive Manufacturing Monitoring

来源：评论

学校读者我要写书评

暂无评论

Classification using hyperdimensional computing: a review with comparative analysis

引用

ARTIFICIAL INTELLIGENCE REVIEW 2025年第6期58卷 1-41页

作者： Verges, Pere Heddes, Mike Nunes, Igor Kleyko, Denis Givargis, Tony Nicolau, Alexandru Univ Calif Irvine Dept Comp Sci Irvine CA 92617 USA Orebro Univ AASS Res Ctr SE-70182 Orebro Sweden Res Inst Sweden Intelligent Syst Lab S-16440 Kista Sweden

hyperdimensional computing (HD), also known as vector symbolic architectures (VSA), is an emerging and promising paradigm for cognitive computing. At its core, HD/VSA is characterized by its distinctive approach to compositionally representing information using high-dimensional randomized vectors. The recent surge in research within this field gains momentum from its computational efficiency stemming from low-resolution representations and ability to excel in few-shot learning scenarios. Nonetheless, the current literature is missing a comprehensive comparative analysis of various methods since each of them uses a different benchmark to evaluate its performance. This gap obstructs the monitoring of the field's state-of-the-art advancements and acts as a significant barrier to its overall progress. To address this gap, this review not only offers a conceptual overview of the latest literature but also introduces a comprehensive comparative study of HD/VSA classification methods. The exploration starts with an overview of the strategies proposed to encode information as high-dimensional vectors. These vectors serve as integral components in the construction of classification models. Furthermore, we evaluate diverse classification methods as proposed in the existing literature. This evaluation encompasses techniques such as retraining and regenerative training to augment the model's performance. To conclude our study, we present a comprehensive empirical study. This study serves as an in-depth analysis, systematically comparing various HD/VSA classification methods using two benchmarks, the first being a set of seven popular datasets used in HD/VSA and the second consisting of 121 datasets being the subset from the UCI Machine Learning repository. To facilitate future research on classification with HD/VSA, we open-sourced the benchmarking and the implementations of the methods we review. Since the considered data are tabular, encodings based on key-value pairs emerge

关键词： hyperdimensional computing Vector symbolic architectures Distributed representations Classification Machine learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Federated Learning with Differentially Private hyperdimensional computing

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 123卷

作者： Piran, Fardin Jalil Chen, Zhiling Imani, Mohsen Imani, Farhad Univ Connecticut Sch Mech Aerosp & Mfg Engn Storrs CT 06269 USA Univ Calif Irvine Dept Comp Sci Irvine CA 92697 USA

Federated Learning (FL) has become a key method for preserving data privacy in Internet of Things (IoT) environments, as it trains Machine Learning (ML) models locally while transmitting only model updates. Despite this design, FL remains susceptible to threats such as model inversion and membership inference attacks, which can reveal private training data. Differential Privacy (DP) techniques are often introduced to mitigate these risks, but simply injecting DP noise into black-box ML models can compromise accuracy, particularly in dynamic IoT contexts, where continuous, lifelong learning leads to excessive noise accumulation. To address this challenge, we propose Federated hyperdimensional computing with Privacy-preserving (FedHDPrivacy), an eXplainable Artificial Intelligence (XAI) framework that integrates neurosymbolic computing and DP. Unlike conventional approaches, FedHDPrivacy actively monitors the cumulative noise across learning rounds and adds only the additional noise required to satisfy privacy constraints. In a real-world application for monitoring manufacturing machining processes, FedHDPrivacy maintains high performance while surpassing standard FL frameworks - Federated Averaging (FedAvg), Federated Proximal (FedProx), Federated Normalized Averaging (FedNova), and Federated Optimization (FedOpt) - by up to 37%. Looking ahead, FedHDPrivacy offers a promising avenue for further enhancements, such as incorporating multimodal data fusion.

关键词： Explainable Artificial Intelligence Internet of Things Federated Learning Differential Privacy hyperdimensional computing

来源：评论

学校读者我要写书评

暂无评论

RelHDx: hyperdimensional computing for Learning on Graphs With FeFET Acceleration

引用

IEEE TRANSACTIONS ON COMPUTERS 2025年第5期74卷 1730-1742页

作者： Kang, Jaeyoung Zhou, Minxuan Xu, Weihong Rosing, Tajana Univ Calif San Diego La Jolla CA 92093 USA

Graph neural networks (GNNs) are a powerful machine learning (ML) method to analyze graph data. The training of GNN has compute and memory-intensive phases along with irregular data movements, which makes in-memory acceleration challenging. We present a hyperdimensional computing (HDC)-based graph ML framework called RelHDx that aggregates node features and graph structure, along with representing node and edge information in high-dimensional space. RelHDx enables single-pass training and inference with simple arithmetic operations, resulting in the efficient design of graph-based ML tasks: node classification and link prediction. We accelerate RelHDx using scalable processing in-memory (PIM) architecture based on emerging ferroelectric FET (FeFET) technology. Our accelerator uses a data allocation optimization and operation scheduler to address the irregularity of the graph and maximize the performance. Evaluation results show that RelHDx offers comparable accuracy to popular GNN-based algorithms while achieving up to $63.8\boldsymbol{\times}$63.8x faster speed on GPU. Our FeFET-based accelerator, RelHDx-PIM, is $32\boldsymbol{\times}$32x faster for node classification, while for link prediction it is $65.4\boldsymbol{\times}$65.4x faster than when running on GPU. Furthermore, RelHDx-PIM improves energy efficiency by four orders of magnitude over GPU. Compared to the state-of-the-art in-memory processing-based GNN accelerator, PIM-GCN [1], RelHDx-PIM is $10\boldsymbol{\times}$10x faster and $986\boldsymbol{\times}$986x more energy-efficient on average.

关键词： FeFETs Training Energy efficiency Encoding Graphics processing units Logic gates Accuracy Vectors Classification algorithms Graph neural networks hyperdimensional computing graph-based machine learning graph neural networks processing-in-memory ferroelectric field-effect transistor

来源：评论

学校读者我要写书评

暂无评论

GlucoseHD: Predicting Glucose Levels Using hyperdimensional computing

IEEE DESIGN & TEST

引用

IEEE DESIGN & TEST 2025年第2期42卷 17-24页

作者： Ponzina, Flavio Gomez, Mialyssa Xu, Congge Rosing, Tajana Simunic Univ Calif San Diego Syst Energy Efficiency Lab La Jolla CA 92093 USA

Editor’s notes: This article proposes an efficient algorithm to predict glucose levels using hyperdimensional computing. Highly accurate glucose level (GL) predictions are of critical importance for people affected by type 1 diabetes. To address this, the article proposes GlucoseHD, a hyperdimensional computing (HDC)-based approach for accurate GL predictions with limited computing and memory budgets. —Ganapati Bhat, Washington State University, USA Pietro Mercati, Intel Labs, USA

关键词： Glucose Predictive models Computational modeling Training Encoding Data models Accuracy hyperdimensional computing Control Glucose Monitoring Glucose Level Predictions

来源：评论

学校读者我要写书评

暂无评论

Federated hyperdimensional computing for hierarchical and distributed quality monitoring in smart manufacturing

引用

INTERNET OF THINGS 2025年 31卷

作者： Chen, Zhiling Hoang, Danny Piran, Fardin Jalil Chen, Ruimin Imani, Farhad Univ Connecticut Sch Mech Aerosp & Mfg Engn Storrs CT 06269 USA

In emerging smart manufacturing, the integration of the Internet of Things (IoT) and edge devices is essential for in-situ sensing, communication, and adaptive learning. Federated Learning (FL) leverages edge-cloud collaboration to preserve data privacy and minimize communication overhead compared to centralized models. However, conventional FL approaches face significant challenges in manufacturing: (1) non-Independent and Identically Distributed (non-IID) data and diverse feature distributions complicate local model training within hierarchical, complex industrial data structures;(2) directly overwriting local models with a global model during updates causes clients to lose critical task-specific information unique to their environments;and (3) transmitting model updates causes communication overhead, limiting scalability. We propose Federated Distributed hyperdimensional computing (FedDHD), an FL framework that employs hyperdimensional computing (HDC) to optimize communication for hierarchical manufacturing data. Unlike neural networks, HDC offers robust performance with lower computational demands and inherent resilience to noisy, non-IID data, enabling FedDHD to naturally handle data heterogeneity and reduce computational burdens on edge devices. FedDHD integrates a hierarchical graph-based learning model with a node pruning module to alleviate computational load and implements a novel client-cloud update strategy leveraging HDC's high-dimensional representations to streamline synchronization, thereby minimizing communication costs and improving scalability. We validate FedDHD through a case study on machining using a Sinumerik edge device, focusing on the geometric quality assessment of two counterbore diameters. FedDHD achieved an F1-score of 95.3% and demonstrated performance improvements of up to 12.6% over state-of-the-art neural network-based FL methods, highlighting its superior efficiency and scalability in complex industrial settings.

关键词： Federated learning Hierarchical learning hyperdimensional computing In-situ quality monitoring

来源：评论

学校读者我要写书评

暂无评论

An Extension to Basis-Hypervectors for Learning from Circular Data in hyperdimensional computing 23

An Extension to Basis-Hypervectors for Learning from Circula...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Igor Nunes Mike Heddes Tony Givargis Alexandru Nicolau Department of Computer Science UC Irvine Irvine USA

ISBN: (纸本)9798350323481

hyperdimensional computing (HDC) is a computation framework based on random vector spaces, particularly useful for machine learning in resource-constrained environments. The encoding of information to the hyperspace is the most important stage in HDC. At its heart are basis-hypervectors, responsible for representing atomic information. We present a detailed study on basis-hypervectors, leading to broad contributions to HDC: 1) an improvement for level-hypervectors, used to encode real numbers; 2) a method to learn from circular data, an important type of information never before addressed in HDC. Results indicate that these contributions lead to considerably more accurate models for classification and regression.

关键词： hyperdimensional computing

来源：评论

学校读者我要写书评

暂无评论

hyperdimensional computing in Industrial Systems: The Use-Case of Distributed Fault Isolation in a Power Plant

引用

IEEE ACCESS 2018年 6卷 30766-30777页

作者： Kleyko, Denis Osipov, Evgeny Papakonstantinou, Nikolaos Vyatkin, Valeriy Lulea Univ Technol Dept Comp Sci Elect & Space Engn S-97187 Lulea Sweden VTT Tech Res Ctr Finland Espoo 02150 Finland Aalto Univ Dept Elect Engn & Automat Espoo 02150 Finland

This paper presents an approach for distributed fault isolation in a generic system of systems. The proposed approach is based on the principles of hyperdimensional computing. In particular, the recently proposed method called Holographic Graph Neuron is used. We present a distributed version of Holographic Graph Neuron and evaluate its performance on the problem of fault isolation in a complex power plant model. Compared to conventional machine learning methods applied in the context of the same scenario the proposed approach shows comparable performance while being distributed and requiring simple binary operations, which allow for a fast and efficient implementation in hardware.

关键词： Vector symbolic architectures Holographic Graph Neuron distributed representation complex systems distributed fault isolation hyperdimensional computing machine learning

来源：评论

学校读者我要写书评

暂无评论

hyperdimensional computing for Blind and One-Shot Classification of EEG Error-Related Potentials

引用

MOBILE NETWORKS & APPLICATIONS 2020年第5期25卷 1958-1969页

作者： Rahimi, Abbas Tchouprina, Artiom Kanerva, Pentti Millan, Jose del R. Rabaey, Jan M. Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA STMicroelectronics Crolles France Berkeley Wireless Res Ctr Berkeley CA 94704 USA Univ Calif Berkeley Redwood Ctr Theoret Neurosci Berkeley CA 94720 USA Ecole Polytech Fed Lausanne EPFL Defitech Fdn Chair Brain Machine Interface CH-1015 Lausanne Switzerland

The mathematical properties of high-dimensional (HD) spaces show remarkable agreement with behaviors controlled by the brain. computing with HD vectors, referred to as "hypervectors," is a brain-inspired alternative to computing with numbers. HD computing is characterized by generality, scalability, robustness, and fast learning, making it a prime candidate for utilization in application domains such as brain-computer interfaces. We describe the use of HD computing to classify electroencephalography (EEG) error-related potentials for noninvasive brain-computer interfaces. Our algorithmnaturallyencodes neural activity recorded from 64 EEG electrodes to a single temporal-spatial hypervector without requiring any electrode selection process. This hypervector represents the event of interest, can be analyzed to identify the most discriminative electrodes, and is used for recognition of the subject's intentions. Using the full set of training trials, HD computing achieves on average 5% higher single-trial classification accuracy compared to a conventional machine learning method on this task (74.5% vs. 69.5%) and offers further advantages: (1) Our algorithm learns fast: using only 34% of training trials it achieves an average accuracy of 70.5%, surpassing the conventional method. (2) Conventional method requires priordomain expertknowledge, or a separate process, to carefully select a subset of electrodes for a subsequent preprocessor and classifier, whereas our algorithm blindly uses all 64 electrodes, tolerates noises in data, and the resulting hypervector is intrinsically clustered into HD space;in addition, most preprocessing of the electrode signal can be eliminated while maintaining an average accuracy of 71.7%.

关键词： Electroencephalogram (EEG) Error-related potentials (ERP) Classification hyperdimensional computing

来源：评论

学校读者我要写书评

暂无评论

hyperdimensional computing With Local Binary Patterns: One-Shot Learning of Seizure Onset and Identification of Ictogenic Brain Regions Using Short-Time iEEG Recordings

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2020年第2期67卷 601-613页

作者： Burrello, Alessio Schindler, Kaspar Benini, Luca Rahimi, Abbas Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland Univ Bern Univ Hosp Bern Inselspital Sleep Wake Epilepsy CtrDept Neurol Bern Switzerland

Objective: We develop a fast learning algorithm combining symbolic dynamics and brain-inspired hyperdimensional computing for both seizure onset detection and identification of ictogenic (seizure generating) brain regions from intracranial electroencephalography (iEEG). Methods: Our algorithm first transforms iEEG time series from each electrode into symbolic local binary pattern codes, from which a holographic distributed representation of the brain state of interest is constructed across all the electrodes and over time in a hyperdimensional space. The representation is used to quickly learn from few seizures, detect their onset, and identify the spatial brain regions that generated them. Results: We assess our algorithm on our dataset that contains 99 short-time iEEG recordings from 16 drug-resistant epilepsy patients being implanted with 36-100 electrodes. For the majority of the patients (ten out of 16), our algorithm quickly learns from one or two seizures and perfectly (100%) generalizes on novel seizures using k-fold cross-validation. For the remaining six patients, the algorithm requires three to six seizures for learning. Our algorithm surpasses the state-of-the-art including deep learning algorithms by achieving higher specificity (94.84% versus 94.77%) and macroaveraging accuracy (95.42% versus 94.96%), and 74x lower memory footprint, but slightly higher average latency in detection (15.9 s versus 14.7 s). Moreover, the algorithm can reliably identify (with a p-value < 0.01) the relevant electrodes covering an ictogenic brain region at two levels of granularity: cerebral hemispheres and lobes. Conclusion and significance: Our algorithm provides: 1) a unified method for both learning and classification tasks with end-to-end binary operations;2) one-shot learning from seizure examples;3) linear computational scalability for increasing number of electrodes;and 4) generation of transparent codes that enables post-translational support for clinical decision m

关键词： iEEG one-shot learning local binary patterns symbolic dynamics hyperdimensional computing seizure detection localization of seizure onset zone

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：