Cross-Correlation Estimation in Artificial Neural Network for Uncertainty Assessment

被引:1
作者
Carratu, Marco [1 ]
Gallo, Vincenzo [1 ]
Laino, Valter [1 ]
Liguori, Consolatina [1 ]
Pietrosanto, Antonio [1 ]
Lundgren, Jan [2 ]
机构
[1] Univ Salerno, Dept Ind Engn, Via Giovanni Paolo II 132, Fisciano, SA, Italy
[2] Mid Sweden Univ, STC Res Ctr, Holmgatan 10, S-85230 Sundsvall, Sweden
来源
2024 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC 2024 | 2024年
关键词
Uncertainty; ISO GUM; Law of Propagation of Uncertainty; Correlation; Artificial Neural Networks; Regression; DEEP LEARNING TECHNIQUES; QUANTIFICATION;
D O I
10.1109/I2MTC60896.2024.10560637
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
One of the main challenges in Artificial Neural Networks (ANNs) is the development of reliable, valid, and reproducible systems. Prediction networks have had a disruptive impact, bringing numerous advantages in various fields, but for their common usage, it's necessary to quantify their quality. In particular, evaluating the uncertainty of the measurements obtained with these approaches allows their correct utilization. This work aims to analyze the covariances of the inputs of different neurons, particularly in those of the hidden layers of ANNs. Evaluating the covariance of the inputs of a single neuron finds primary use in the law of propagation of uncertainty, particularly for evaluating the correlation term in mathematical development, as defined by ISO GUM. Based on numerical evaluation, the proposed procedure aims to evaluate the PDFs of inputs to individual nodes and, therefore, the correlations among all inputs propagating within the network architecture.
引用
收藏
页数:6
相关论文
共 36 条
[11]   An enhanced Smart Sampling algorithm based on Deep Learning [J].
Carratu, Marco ;
Dello Iacono, Salvatore ;
Gallo, Vincenzo ;
Paciello, Vincenzo ;
Monte, Gustavo ;
Espirito-Santo, Antonio .
2023 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, I2MTC, 2023,
[12]  
Carratu M, 2023, IEEE T INSTRUM MEAS, V72, DOI [10.1109/TIM.2023.3318684, 10.1109/TIM.2023.3242018]
[13]   A deep learning approach for the development of an Early Earthquake Warning system [J].
Carratu, Marco ;
Gallo, Vincenzo ;
Paciello, Vincenzo ;
Pietrosanto, Antonio .
2022 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC 2022), 2022,
[14]   Metrological Characterization of a Novel Microsensor Platform for Activated Carbon Filters Monitoring [J].
Cerro, Gianni ;
Ferdinandi, Marco ;
Ferrigno, Luigi ;
Laracca, Marco ;
Molinara, Mario .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2018, 67 (10) :2504-2515
[15]   A Deep Learning Model for Smart Manufacturing Using Convolutional LSTM Neural Network Autoencoders [J].
Essien, Aniekan ;
Giannetti, Cinzia .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (09) :6069-6078
[16]  
Gal Y, 2016, PR MACH LEARN RES, V48
[17]   A survey of uncertainty in deep neural networks [J].
Gawlikowski, Jakob ;
Tassi, Cedrique Rovile Njieutcheu ;
Ali, Mohsin ;
Lee, Jongseok ;
Humt, Matthias ;
Feng, Jianxiang ;
Kruspe, Anna ;
Triebel, Rudolph ;
Jung, Peter ;
Roscher, Ribana ;
Shahzad, Muhammad ;
Yang, Wen ;
Bamler, Richard ;
Zhu, Xiao Xiang .
ARTIFICIAL INTELLIGENCE REVIEW, 2023, 56 (SUPPL 1) :1513-1589
[18]   A survey of deep learning techniques for autonomous driving [J].
Grigorescu, Sorin ;
Trasnea, Bogdan ;
Cocias, Tiberiu ;
Macesanu, Gigel .
JOURNAL OF FIELD ROBOTICS, 2020, 37 (03) :362-386
[19]   NEURAL NETWORK ENSEMBLES [J].
HANSEN, LK ;
SALAMON, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (10) :993-1001
[20]   Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods [J].
Huellermeier, Eyke ;
Waegeman, Willem .
MACHINE LEARNING, 2021, 110 (03) :457-506