检索结果-内蒙古大学图书馆

Orientation Detection Method Based on Non-Imaging Concentrator System and hyperparameter search

IEEE PHOTONICS TECHNOLOGY LETTERS 2025年第1期37卷 25-28页

作者： Chen, Tianqi Xie, Zhiwei Qiu, Qiao Ru, Zhanqiang Wang, Fei Chang, Shengli Hunan Univ Sch Phys & Elect Changsha 410082 Peoples R China Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & Nanobion Suzhou 215123 Peoples R China

The concentrator system is widely used in photovoltaic power generation technology. This letter introduces the concentrator system into orientation detection. It proposes an innovative method combining a non-imaging concentrator system, a data collection electronic system, and a deep residual network(ResNet) algorithm optimized through hyperparameter search. The concentrator system comprises a primary optical element(POE) and a secondary optical element(SOE) array, while the electronic system is built around a PIN photodiode array. Experimental results validate the feasibility of this novel orientation detection method for the first time. This research offers a fresh perspective and technical foundation for orientation detection and identification.

关键词： Detectors Accuracy Optical scattering Optical reflection Azimuth Adaptive optics Optical sensors Complexity theory Training Costs Orientation detection concentrator system primary optical element secondary optical element hyperparameter search

来源：评论

学校读者我要写书评

暂无评论

A novel hyperparameter search approach for accuracy and simplicity in disease prediction risk scoring

引用

JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 2024年第8期31卷 1763-1773页

作者： Lu, Yajun Duong, Thanh Miao, Zhuqi Thieu, Thanh Lamichhane, Jivan Ahmed, Abdulaziz Delen, Dursun Jacksonville State Univ Dept Management & Mkt Jacksonville AL 36265 USA Univ S Florida Dept Comp Sci & Engn Tampa FL 33620 USA H Lee Moffitt Canc Ctr & Res Inst Dept Machine Learning Tampa FL 33612 USA State Univ New York New Paltz Sch Business New Paltz NY 12561 USA Univ S Florida Dept Oncol Sci Morsani Coll Med Tampa FL 33612 USA State Univ New York Upstate Med Univ Syracuse NY 13210 USA Univ Alabama Birmingham Sch Hlth Profess Dept Hlth Serv Adm Birmingham AL 35233 USA Oklahoma State Univ Ctr Hlth Syst Innovat Dept Management Sci & Informat Syst Business Bldg Stillwater OK 74078 USA Istinye Univ Fac Engn & Nat Sci Dept Ind Engn TR-34396 Istanbul Turkiye

Objective Develop a novel technique to identify an optimal number of regression units corresponding to a single risk point, while creating risk scoring systems from logistic regression-based disease predictive models. The optimal value of this hyperparameter balances simplicity and accuracy, yielding risk scores of small scale and high accuracy for patient risk *** and Methods The proposed technique applies an adapted line search across all potential hyperparameter values. Additionally, DeLong test is integrated to ensure the selected value produces an accuracy insignificantly different from the best achievable risk score accuracy. We assessed the approach through two case studies predicting diabetic retinopathy (DR) within six months and hip fracture readmissions (HFR) within 30 days, involving cohorts of 90 400 diabetic patients and 18 065 hip fracture *** Our scores achieve accuracies insignificantly different from those obtained by existing approaches, reaching AUROCs of 0.803 and 0.645 for DR and HFR predictions, respectively. Regarding the scale, our scores ranged 0-53 for DR and 0-15 for HFR, while scores produced by existing methods frequently spanned hundreds or *** According to the assessment, our risk scores offer simple and accurate predictions for diseases. Furthermore, our new DR score provides a competitive alternative to state-of-the-art risk scores for DR, while our HFR case study presents the first risk score for this *** Our technique offers a generalizable framework for crafting precise risk scores of compact scales, addressing the demand for user-friendly and effective risk stratification tool in healthcare.

关键词： disease prediction risk scoring system hyperparameter search electronic health record

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of CNN Models in Urban Acoustic Event Recognition Through MFCC hyperparameter search

Performance Evaluation of CNN Models in Urban Acoustic Event...

引用

2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023

作者： Tangarife, Ricardo Velásquez, Ricardo A. Rivera, Fredy University of Antioquia Dept. Electronics Engineering Medellín Colombia University of Antioquia Dept. Computer Science Medellín Colombia

ISBN: (纸本)9798350327595

This paper focuses on acoustic event recognition, a significant research area in various fields, including security, medicine, and entertainment. The study explores the design space of combining convolutional neural networks with Mel Frequency Cepstral Coefficients to extract audio features. This work explicitly investigates three acoustic events relevant to citizen security: gunshots, screams, and sirens. We aim to find the optimal combination of hyperparameters to train accurate models with low computational requirements. The proposed approach achieved impressive F1-Scores of 95% for sirens, 97.2% for gunshots, and 99% for screams. Furthermore, considering computational complexity, our results demonstrate that these sounds could be utilized in real-time acoustic event recognition systems for citizen security applications. © 2023 IEEE.

关键词： Acoustic Event Recognition Audio Feature Extraction hyperparameter search Machine Learning MFCC

来源：评论

学校读者我要写书评

暂无评论

A protocol for trustworthy EEG decoding with neural networks

引用

NEURAL NETWORKS 2025年 182卷 106847页

作者： Borra, Davide Magosso, trustworthy Elisa Ravanelli, Mirco Univ Bologna Dept Elect Elect & Informat Engn Guglielmo Marconi Cesena Forli Italy Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada Mila Quebec Inst Montreal PQ Canada

Deep learning solutions have rapidly emerged for EEG decoding, achieving state-of-the-art performance on a variety of decoding tasks. Despite their high performance, existing solutions do not fully address the challenge posed by the introduction of many hyperparameters, defining data pre-processing, network architecture, network training, and data augmentation. Automatic hyperparameter search is rarely performed and limited to network-related hyperparameters. Moreover, pipelines are highly sensitive to performance fluctuations due to random initialization, hindering their reliability. Here, we design a comprehensive protocol for EEG decoding that explores the hyperparameters characterizing the entire pipeline and that includes multi-seed initialization for providing robust performance estimates. Our protocol is validated on 9 datasets about motor imagery, P300, SSVEP, including 204 participants and 26 recording sessions, and on different deep learning models. We accompany our protocol with extensive experiments on the main aspects influencing it, such as the number of participants used for hyperparameter search, the split into sequential simpler searches (multi-step search), the use of informed vs. non-informed search algorithms, and the number of random seeds for obtaining stable performance. The best protocol included 2-step hyperparameter search via an informed search algorithm, with the final training and evaluation performed using 10 random initializations. The optimal trade-off between performance and computational time was achieved by using a subset of 3-5 participants for hyperparameter search. Our protocol consistently outperformed baseline state-of-the-art pipelines, widely across datasets and models, and could represent a standard approach for neuroscientists for decoding EEG in a trustworthy and reliable way.

关键词： Electroencephalography Single-trial EEG decoding Deep learning Convolutional neural networks hyperparameter search Brain-Computer Interfaces

来源：评论

学校读者我要写书评

暂无评论

Grouper: Accelerating hyperparameter searching in Deep Learning Clusters With Network Scheduling

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2020年第3期17卷 1879-1895页

作者： Zhou, Pan Yu, Hongfang Sun, Gang Univ Elect Sci & Technol China Minist Educ Key Lab Opt Fiber Sensing & Commun Chengdu 611731 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China

Training a high-accuracy model requires trying hundreds of configurations of hyperparameters to search for the optimal configuration. It is common to launch a group of training jobs (named cojob) with different configurations at the same time and stop the jobs performing worst every stage (i.e., a certain number of iterations). Thus deep learning requires minimizing stage completion time (SCT) to accelerate the searching. To quickly complete the stages, each job in the cojob typically uses multiple GPUs to perform distributed training. The GPUs exchange data per iteration to synchronize their models through the network. However, data transfers of DL jobs compete for network bandwidth since the GPU cluster hosts a number of cojobs from various users, resulting in network congestion and consequently a large SCT for cojobs. Existing flow schedulers aimed at reducing flow/coflow/job completion time mismatch the requirement of hyperparameter searching. In this paper, we implement a system Grouper to minimize average SCT for cojobs. Grouper adopts a well-designed algorithm to permute stages of cojobs and schedules flows from different stages in the order of the permutation. The extensive testbed experiments and simulations show that Grouper outperforms advanced network designs Baraat, Sincrona, and per-flow fair share.

关键词： Training Servers Data models Graphics processing units Distributed databases Bandwidth Machine learning Deep learning hyperparameter search flow scheduling stage completion time

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementations of Kernel Normalised Least Mean Squares Processors

引用

ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS 2017年第4期10卷 26.1-26.1页

作者： Fraser, Nicholas J. Lee, Junkyu Moss, Duncan J. M. Faraone, Julian Tridgell, Stephen Jin, Craig T. Leong, Philip H. W. Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

Kernel adaptive filters (KAFs) are online machine learning algorithms which are amenable to highly efficient streaming implementations. They require only a single pass through the data and can act as universal approximators, i.e. approximate any continuous function with arbitrary accuracy. KAFs are members of a family of kernel methods which apply an implicit non-linear mapping of input data to a high dimensional feature space, permitting learning algorithms to be expressed entirely as inner products. Such an approach avoids explicit projection into the feature space, enabling computational efficiency. In this paper, we propose the first fully pipelined implementation of the kernel normalised least mean squares algorithm for regression. Independent training tasks necessary for hyperparameter optimisation fill pipeline stages, so no stall cycles to resolve dependencies are required. Together with other optimisations to reduce resource utilisation and latency, our core achieves 161 GFLOPS on a Virtex 7 XC7VX485T FPGA for a floating point implementation and 211 GOPS for fixed point. Our PCI Express based floating-point system implementation achieves 80% of the core's speed, this being a speedup of 10x over an optimised implementation on a desktop processor and 2.66x over a GPU.

关键词： FPGAs machine learning hyperparameter search pipeline

来源：评论

学校读者我要写书评

暂无评论

Leader population learning rate schedule

引用

INFORMATION SCIENCES 2023年第1期623卷 455-468页

作者： Wei, Jia Zhang, Xingjun Zhuo, Zhimin Ji, Zeyu Wei, Zheng Li, Jingbo Li, Qianyang Xi An Jiao Tong Univ Sch Comp Sci & Technol Xian 710049 Peoples R China Beijing Inst Elect Syst Engn Beijing 100854 Peoples R China

The successful application of modern deep neural network models is deeply influenced by the choice of hyperparameters. As one of the most important hyperparameters, the Learning Rate (LR) needs to be fine-tuned. In order to train models that can perform better, finding a suitable LR schedule quickly has become a pressing problem. Current research often relies on manual use of parallel search methods such as grid search, or serial methods such as Bayesian. However, the variety and number of models and datasets result in a very large LR space, and these methods consume significant resources to find only sub-optimal static LR schedules within a given time frame. It was found that in the currently widely used Distributed Data Parallel (DDP) deep learning, where multiple nodes themselves con-stitute the population, it is possible to use population algorithms to optimise the searched LR schedule dynamically throughout the training process with little additional training time. To maximise the potential of both the searched LR schedule and the population opti-misation of the participating multi-nodes, this paper proposes a Leader Population Learning Rate Schedule (LPLRS) for the DDP deep learning environment, which continu-ously explores for better learning rates in the neighbourhood of the searched LR schedule and guides the subsequent training process. LPLRS achieves higher model classification accuracy on the Cifar 10&100 test datasets on the state-of-the-art Wide Residual Network with Sharpness-Aware Minimization (WRN(SAM)) model compared to the latest SGDR, CLR, and StepLR learning rate schedules.(c) 2022 Elsevier Inc. All rights reserved.

关键词： Deep learning Distributed training hyperparameter search Data parallel Population algorithm Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep chemometrics using one-dimensional convolutional neural networks for predicting crude oil properties from FTIR spectral data

引用

CANADIAN JOURNAL OF CHEMICAL ENGINEERING 2023年第12期101卷 6688-6700页

作者： Ta, Souvik Alizadeh, Shahla Samavedham, Lakshminarayanan Ray, Ajay K. Western Univ Dept Chem & Biochem Engn London ON Canada Natl Univ Singapore Dept Chem & Biomol Engn Singapore Singapore

The determination of physicochemical properties of crude oils is a very important and time-intensive process that needs elaborate laboratory procedures. Over the last few decades, several correlations have been developed to estimate these properties, but they have been very limited in their scope and range. In recent years, methods based on spectral data analysis have been shown to be very promising in characterizing petroleum crude. In this work, the physicochemical properties of crude oils using Fourier transform infrared (FTIR) spectrums are predicted. A total of 107 samples of FTIR spectral data consisting of 6840 wavenumbers is used. One dimensional convolutional neural networks (CNNs) were used employing FTIR spectral data as the one-dimensional input and Keras and TensorFlow were used for model building. The Root Mean Square Error decreased from 160 to around 60 for viscosity when compared to previous machine learning methods like partial least squares (PLS), principal component regression (PCR), and partial least squares regression with genetic algorithm (PLS-GA) on the same data. The important hyper-parameters of the CNN were optimized. In addition, a comparison of results obtained with different neural network architectures is presented. Some common preprocessing techniques were also tested on the spectral data to determine their impact on model performance. To increase interpretability, the intermediate neural network layers were analyzed to reveal what the convolutions represented, and sensitivity analysis was done to gather key insights about the wavenumbers that were the most important for prediction of the crude oil properties using the neural network.

关键词： deep learning in spectra hyperparameter search neural architecture search one dimensional convolutional neural networks property prediction using deep learning

来源：评论

学校读者我要写书评

暂无评论

HyperSTAR: Task-Aware hyperparameter Recommendation for Training and Compression

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2024年第6期132卷 1913-1927页

作者： Liu, Chang Mittal, Gaurav Karianakis, Nikolaos Fragoso, Victor Yu, Ye Fu, Yun Chen, Mei Northeastern Univ Boston MA USA Microsoft Cloud AI Redmond WA 98052 USA

hyperparameter optimization (HPO) methods alleviate the significant effort required to obtain hyperparameters that perform optimally on visual learning problems. Existing methods are computationally inefficient because they are task agnostic (i.e., they do not adapt to a given task). We present HyperSTAR (System for Task Aware hyperparameter Recommendation), a task-aware HPO algorithm that improves HPO efficiency for a target dataset by using prior knowledge from previous hyperparameter searches to recommend effective hyperparameters conditioned on the target dataset. HyperSTAR ranks and recommends hyperparameters by predicting their performance on the target dataset. To do so, it learns a joint datasethyperparameter space in an end-to-end manner that enables its performance predictor to use previously found effective hyperparameters for other similar tasks. The hyperparameter recommendations of HyperSTAR combined with existing HPO techniques lead to a task-aware HPO system that reduces the time to find the optimal hyperparameters for the target learning problem. Our experiments on image classification, object detection, and model pruning validate that HyperSTAR reduces the evaluation of different hyperparameter configurations by about 50% compared to existing methods and, when combined with Hyperband, uses only 25% of the budget required by the vanilla Hyperband and Bayesian Optimized Hyperband to achieve the best performance.

关键词： hyperparameter search AutoML Warm start Meta-learning Image classification Object detection Model pruning

来源：评论

学校读者我要写书评

暂无评论

Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching

引用

JOURNAL OF MACHINE LEARNING REsearch 2023年第1期24卷 1-51页

作者： da Silva, Eliezer de Souza Kusmierczyk, Tomasz Hartmann, Marcelo Klami, Arto Norwegian Univ Sci & Technol Dept Comp Sci Trondheim Norway Fundacao Getulio Vargas Sch Appl Math Rio De Janeiro Brazil Univ Helsinki Dept Comp Sci Helsinki Finland

The behavior of many Bayesian models used in machine learning critically depends on the choice of prior distributions, controlled by some hyperparameters typically selected through Bayesian optimization or cross-validation. This requires repeated, costly, posterior inference. We provide an alternative for selecting good priors without carrying out posterior inference, building on the prior predictive distribution that marginalizes the model parameters. We estimate virtual statistics for data generated by the prior predictive distribution and then optimize over the hyperparameters to learn those for which the virtual statistics match the target values provided by the user or estimated from (a subset of) the observed data. We apply the principle for probabilistic matrix factorization, for which good solutions for prior selection have been missing. We show that for Poisson factorization models we can analytically determine the hyperparameters, including the number of factors, that best replicate the target statistics, and we empirically study the sensitivity of the approach for the model mismatch. We also present a model-independent procedure that determines the hyperparameters for general models by stochastic optimization and demonstrate this extension in the context of hierarchical matrix factorization models.

关键词： Bayesian modeling prior specification hyperparameter search probabilistic matrix factorization

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：