检索结果-内蒙古大学图书馆

MACHINE LEARNING 2022年第2期111卷 625-650页

作者： Fraccaroli, Michele Lamma, Evelina Riguzzi, Fabrizio Univ Ferrara DE Dept Engn Via Saragat 1 I-44122 Ferrara Italy Univ Ferrara DMI Dept Math & Comp Sci Via Saragat 1 I-44122 Ferrara Italy

hyper-parameter optimization (HPO) occupies a fundamental role in Deep Learning systems due to the number of hyper-parameters (HPs) to be set. The state-of-the-art of HPO methods are Grid Search, Random Search and Bayesian optimization. The first two methods try all possible combinations and random combination of the HPs values, respectively. This is performed in a blind manner, without any information for choosing the new set of HPs values. Bayesian optimization (BO), instead, keeps track of past results and uses them to build a probabilistic model mapping HPs into a probability density of the objective function. Bayesian optimization builds a surrogate probabilistic model of the objective function, finds the HPs values that perform best on the surrogate model and updates it with new results. In this paper, we improve BO applied to Deep Neural Network (DNN) by adding an analysis of the results of the network on training and validation sets. This analysis is performed by exploiting rule-based programming, and in particular by using Probabilistic Logic Programming. The resulting system, called Symbolic DNN-Tuner, logically evaluates the results obtained from the training and the validation phase and, by applying symbolic tuning rules, fixes the network architecture, and its HPs, therefore improving performance. We also show the effectiveness of the proposed approach, by an experimental evaluation on literature and real-life datasets.

关键词： Deep learning hyper-parameter optimization Probabilistic logic programming

来源：评论

学校读者我要写书评

暂无评论

A Practical Framework for Designing and Deploying Tiny Deep Neural Networks on Microcontrollers

A Practical Framework for Designing and Deploying Tiny Deep ...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Zhuang, Brenda Pau, Danilo MathWorks Natick United States STMicroelectronics Agrate Brianza Italy

ISBN: (纸本)9798350324136

For many applications, Deep Neural Networks (DNNs) trained on powerful CPUs and GPUs are expected to efficiently perform inference on tiny devices. However, deploying productively un-constrained complex models to microcontrollers (MCUs) remains a time-consuming task. In this paper, a comprehensive methodology is presented that combines advanced optimization techniques in hyperparameter search, model compression, and deployability evaluation using benchmark *** typically have low-power processors, limited embedded RAM memory and FLASH storage, providing orders of magnitude fewer computational resources than what cloud assets offer. Designing DNNs for such platforms requires effective strategies to balance high accuracy performance with low memory usage and inference latency. To address this challenge, Bayesian optimization has been applied, a powerful complexity-bounded technique, to hyperparameter tuning to select tiny model architecture candidates. Several pruning and quantization methods have been developed to compress all the models and evaluated the numerical performance after compression. Additionally, cloud-based deployment tools have been utilized to iteratively validate the on-device memory and latency performance on off-The-shelf MCUs. Through evaluating the benchmarks against the stringent requirements of tiny devices at the edge, practical insights have been gained into these *** image classification applications have been applied on a variety of STM32 MCUs. The practical framework can: A) maintain top-1 classification accuracy within tolerance from the floating-point network after compression;b) reduce memory footprint by at least 4 times;c) reduce inference runtime significantly by avoiding external RAM usage;d) adaptable to many different applications. © 2024 IEEE.

关键词： Bayesian optimization Deep learning deployment hyper-parameter optimization microcontrollers model compression resource constraints

来源：评论

学校读者我要写书评

暂无评论

Batch sequential adaptive designs for global optimization

引用

JOURNAL OF THE KOREAN STATISTICAL SOCIETY 2022年第3期51卷 780-802页

作者： Xiao, Yao Ning, Jianhui Xiong, Zikang Qin, Hong Zhongnan Univ Econ & Law Sch Stat & Math Wuhan 430073 Hubei Peoples R China Cent China Normal Univ Sch Math & Stat Wuhan 430079 Hubei Peoples R China

Efficient global optimization (EGO) is one of the most popular sequential adaptive design (SAD) methods for expensive black-box optimization problems. A well-recognized weakness of the original EGO in complex computer experiments is that it is serial, and hence the modern parallel computing techniques cannot be utilized to speed up the running of simulator experiments. For those multiple points EGO methods, the heavy computation and points clustering are the obstacles. In this work, a novel batch SAD method, named "Accelerated EGO", is forwarded by using a refined sampling/importance resampling (SIR) method to search the points with large expected improvement (EI) values. The computation burden of the new method is much lighter, and the points clustering is also avoided. The efficiency of the proposed batch SAD is validated by nine classic test functions with dimension from 2 to 12. The empirical results show that the proposed algorithm indeed can parallelize original EGO, and gain much improvement compared against the other parallel EGO algorithm especially under high-dimensional case. Additionally, the new method is applied to the hyper-parameter tuning of support vector machine (SVM) and XGBoost models in machine learning. Accelerated EGO obtains comparable cross validation accuracy with other methods and the CPU time can be reduced a lot due to the parallel computation and sampling method.

关键词： Computer experiments Efficient global optimization Sequential adaptive designs Expected improvement hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

A Recent Publications Survey on Reinforcement Learning for Selecting parameters of Meta-Heuristic and Machine Learning Algorithms 13

A Recent Publications Survey on Reinforcement Learning for S...

引用

13th International Conference on Cloud Computing and Services Science (CLOSER)

作者： Chernigovskaya, Maria Kharitonov, Andrey Turowski, Klaus Otto von Guericke Univ Fac Comp Sci Magdeburg Germany

ISBN: (纸本)9789897586507

Nowadays, meta-heuristic and machine learning algorithms are often used for a variety of tasks in cloud computing operations. The choice of hyper-parameter values has a direct impact on the performance of these algorithms, making hyper-parameter optimization (HPO) an important research field for facilitating the widespread application of machine learning and meta-heuristics for problem-solving. Manual parameterization of these algorithms is an inefficient method, which motivates researchers to look for a new and more efficient approach to tackle this challenge. One such innovative approach is Deep Reinforcement Learning (DRL), which has recently demonstrated a lot of potential in solving complex problems. In this work, we aim to explore this topic more thoroughly and shed light on the application of DRL-based techniques in HPO, specifically for Machine Learning and Heuristics/Meta-heuristics-based algorithms. We approach the problem by conducting a systematic literature review of the recently published literature and summarizing the results of the analysis. Based on the conducted literature review, within the selected sources, we identified 14 relevant publications and a clear research gap in the cloud-specific use case for HPO via DRL.

关键词： Reinforcement Learning Deep Reinforcement Learning hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement 23

A Generalized Physical-knowledge-guided Dynamic Model for Un...

引用

31st ACM International Conference on Multimedia (MM)

作者： Mu, Pan Xu, Hanning Liu, Zheyuan Wang, Zheng Chan, Sixian Bai, Cong Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou Peoples R China

ISBN: (纸本)9798400701085

Underwater images often suffer from color distortion and low contrast resulting in various image types, due to the scattering and absorption of light by water. While it is difficult to obtain high-quality paired training samples with a generalized model. To tackle these challenges, we design a Generalized Underwater image enhancement method via a Physical-knowledge-guided Dynamic Model (short for GUPDM). In particular, to cover complex underwater scenes, this study changes the global atmosphere light and the transmission to simulate various underwater image types through the formation model. We then design an Atmosphere-based Dynamic Structure (ADS) and Transmission-guided Dynamic Structure (TDS) that use dynamic convolutions to adaptively extract prior information from underwater images and generate parameters for Prior-based Multi-scale Structure (PMS). These two modules enable the network to select appropriate parameters for various water types adaptively. Besides, the multi-scale feature extraction module in PMS uses convolution blocks with different kernel sizes and obtains weights for each feature map via channel attention block. The source code will be available at https://***/shiningZZ/GUPDM.

关键词： Physical-Knowledge-Guided Model Deep Learning Underwater Image Enhancement hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

GEP-DL4Mol: A Novel Molecular Deep-learning Model optimization Framework for Boosting Molecular Properties Prediction

GEP-DL4Mol: A Novel Molecular Deep-learning Model Optimizati...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Peng, Yuzhong Zhang, Hao Zhang, Ziqiao Lin, Yanmei Zhou, Shuigeng Qiao, Shaojie Nanning Normal University Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China Fudan University Shanghai Key Lab of Intelligent Information Processing Shanghai China Nanning Normal University Undergraduate College Nanning China Chengdu University of Information Technology School of Software Engineering Chengdu China

ISBN: (纸本)9798350337488

High-performance molecular property prediction is one of the essential problems in many research fields. Although Deep Learning models (DLMs) have the strong potential to predict molecular property, the search space of their neural structure and hyperparameters is too huge to enumerate all possibilities, which implies that one will be difficult to get a optimal configuration solution, or even build a DLM with poor performance. To tackle the aforementioned problem, we first abstractly map various types of supervised DLMs for chemical molecular property prediction under a unified molecular DLM conceptualization. Then, we develop a self-learning molecular DLMs construction and optimization framework, called GEP-DL4Mol, based on the unified supervised molecular DLM conceptualization and Gene Expression Programming. Experiments on eight benchmark datasets including 19 property prediction tasks were conducted to evaluate the performance of the proposed method. Experimental results show that the proposed method outperforms other methods. © 2023 IEEE.

关键词： deep learning deep neural network optimization gene expression programming hyper-parameter optimization molecular modeling Molecular property prediction

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparison of Cross-Validation Procedures for Portfolio Selection

An Empirical Comparison of Cross-Validation Procedures for P...

引用

IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr)

作者： Paskaramoorthy, Andrew van Zyl, Terence L. Gebbie, Tim Univ Witwatersrand Comp Sci & Appl Math Johannesburg South Africa Univ Johannesburg Inst Intelligent Syst Johannesburg South Africa Univ Cape Town Dept Stat Sci Cape Town South Africa

ISBN: (纸本)9781665442343

We present the constrained portfolio selection problem as a learning problem requiring hyper-parameter specification. In practice, hyper-parameters are typically selected using a validation procedure, of which there are several widely-used alternatives. However, the performance of different validation procedures is problem dependent and has not been investigated for the portfolio selection problem. This study examines the behaviour of common validation procedures, including holdout, k-fold cross-validation, Monte Carlo cross-validation, and repeated k-fold cross-validation for estimating performance and selecting hyper-parameters for constrained portfolio selection. The results demonstrate that repeated k-fold cross-validation is the best performing procedure and recommend using 5 repetitions with 3 <= k <= 10 in practice.

关键词： cross-validation portfolio optimization portfolio selection constrained portfolio optimization machine learning hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Interpretable Machine Learning Framework to Predict the Glass Transition Temperature of Polymers

引用

POLYMERS 2024年第8期16卷 1049页

作者： Uddin, Md. Jamal Fan, Jitang Beijing Inst Technol Sch Mechatron Engn Beijing 100081 Peoples R China

The glass transition temperature of polymers is a key parameter in meeting the application requirements for energy absorption. Previous studies have provided some data from slow, expensive trial-and-error procedures. By recognizing these data, machine learning algorithms are able to extract valuable knowledge and disclose essential insights. In this study, a dataset of 7174 samples was utilized. The polymers were numerically represented using two methods: Morgan fingerprint and molecular descriptor. During preprocessing, the dataset was scaled using a standard scaler technique. We removed the features with small variance from the dataset and used the Pearson correlation technique to exclude the features that were highly connected. Then, the most significant features were selected using the recursive feature elimination method. Nine machine learning techniques were employed to predict the glass transition temperature and tune their hyperparameters. The models were compared using the performance metrics of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). We observed that the extra tree regressor provided the best results. Significant features were also identified using statistical machine learning methods. The SHAP method was also employed to demonstrate the influence of each feature on the model's output. This framework can be adaptable to other properties at a low computational expense.

关键词： machine learning feature selection hyper-parameter optimization glass transition temperature polymer

来源：评论

学校读者我要写书评

暂无评论

ROBUST SPEAKER VERIFICATION USING POPULATION-BASED DATA AUGMENTATION 47

ROBUST SPEAKER VERIFICATION USING POPULATION-BASED DATA AUGM...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Lin, Weiwei Mak, Man-Wai Hong Kong Polytech Univ Dept Elect & Informat Engn Hong Kong Peoples R China

ISBN: (纸本)9781665405409

Speaker recognition under environments with a low signal-to-noise ratio (SNR) and high reverberation level has always been challenging. Data augmentation can be applied to simulate the adverse environments that a speaker recognition system may encounter. Typically, the augmentation parameters are manually set. Recently, automatic hyper-parameter optimization using population-based learning has shown promising results. This paper proposes a population-based searching strategy for optimizing the augmentation parameters. We refer to the resulting augmentation as populationbased augmentation (PBA). Instead of finding a fixed set of hyper-parameters, PBA learns a scheduler for setting the hyper-parameters. This strategy offers a considerable computation advantage over the grid search. We obtained highperformance augmentation policies using a population of six networks only. With PBA, we achieved an EER of 3.98% on the VOiCES19 evaluation set.

关键词： Robust speaker verification data augmentation population-based learning hyper-parameter optimization

来源：评论

学校读者我要写书评

暂无评论

Optimized deep learning in a metaverse environment for autistic child support

引用

International Journal of Information Technology (Singapore) 2025年 1-8页

作者： Sayed, Gehad Ismail Dahy, Ghada Hassanien, Aboul Ella School of Computer Science Canadian International College (CIC) Cairo Egypt Scientific Research School of Egypt (SRSEG) Cairo Egypt Faculty of Computers and Artificial Intelligence Cairo University Cairo Egypt

Autism spectrum disorder (ASD) children face communication, behavior, and social challenges, making it challenging for caregivers to provide constant supervision and address unusual behaviors. To address this, the proposed system monitors the emotions of an ASD child by analyzing their facial expressions. When the system detects emotions such as fear, sadness, or anger, it generates a spoken avatar of the child's caregiver, to provide immediate support and intervention. The proposed system comprises two main components working concurrently: real-time facial emotion detection and talking avatar generation. For the real-time emotion detection component, an optimized version of the Xception deep-learning architecture is introduced, utilizing a modified Hippopotamus optimization algorithm (MHO). The optimized Xception model demonstrated superior performance across three benchmark datasets. The model achieved impressive accuracies of 99.61% on Extended CK + 48, 82.68% on FER2013, and 97.18% on autistic children emotions dataset. Additionally, the results demonstrate that MHO algorithm significantly enhances the Xception model's performance and the overall real-time emotion detection system. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Autism Spectrum Disorder Autistic Children Deep Learning Facial Emotions hyper-parameter optimization Metaverse

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：