Filters








133 Hits in 3.7 sec

Rolling Bearing Fault Diagnosis Based on STFT-Deep Learning and Sound Signals

Hongmei Liu, Lianfeng Li, Jian Ma
2016 Shock and Vibration  
A deep learning network has the ability to automatically learn good characteristics from input data in an unsupervised fashion, and its unique layer-wise pretraining and fine-tuning using the backpropagation  ...  strategy can solve the difficulties of training deep multilayer networks.  ...  Acknowledgments This research was supported by the National Natural Science Foundation of China (Grant nos. 51605014, 61074083, 51575021, and 51105019) as well as the Technology Foundation Program of National  ... 
doi:10.1155/2016/6127479 fatcat:irc7ahmcojdhdjtaueiooggrye

Feature Extraction of Anomaly Electricity Usage Behavior in Residence Using Autoencoder

Chia-Wei Tsai, Kuei-Chun Chiang, Hsin-Yuan Hsieh, Chun-Wei Yang, Jason Lin, Yao-Chung Chang
2022 Electronics  
The main subtopic of this subject is the identification of abnormal electricity consumption behaviors.  ...  However, due to the significant number of dimensions and a large amount of redundant information in these low-level features, the training efficiency of the model is often low.  ...  According to the neural network architecture, an autoencoder comprises an encoder and decoder, which have neural networks with the same number of neurons.  ... 
doi:10.3390/electronics11091450 fatcat:nww2zlwc7ffhpdtkvnusrn4qwe

A Sparse Coding Interpretation of Neural Networks and Theoretical Implications [article]

Joshua Bowren
2021 arXiv   pre-print
Theories abound for the aptitude of convolutional neural networks for image classification, but less is understood about why such models would be capable of complex visual tasks such as inference and anomaly  ...  Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful  ...  While the input data will not be fit perfectly, a perfect fit of the finite input data set is probably an example of overfitting which may be the case in convolutional neural networks.  ... 
arXiv:2108.06622v2 fatcat:y6tsui52szhw7fyryilcu6vt54

Learning Deep Architectures for AI

Y. Bengio
2009 Foundations and Trends® in Machine Learning  
This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models  ...  In addition to the difficulty of coming up with the appropriate intermediate abstractions, the number of visual and semantic categories (such as MAN) that we would like an "intelligent" machine to capture  ...  Acknowledgments The author is particularly grateful for the inspiration from and constructive input from Yann LeCun, Aaron Courville, Olivier Delalleau, Dumitru Erhan, Pascal Vincent, Geoffrey Hinton,  ... 
doi:10.1561/2200000006 fatcat:pqujlozkonasra65suwxpvvuou

Recent advances in visual and infrared face recognition—a review

Seong G. Kong, Jingu Heo, Besma R. Abidi, Joonki Paik, Mongi A. Abidi
2005 Computer Vision and Image Understanding  
IR imagery represents a viable alternative to visible imaging in the search for a robust and practical identification system.  ...  However, the performance of visual face recognition may degrade under poor illumination conditions or for subjects of various skin colors.  ...  Acknowledgment This research was supported by the Office of Naval Research under Grant No. N000143010022.  ... 
doi:10.1016/j.cviu.2004.04.001 fatcat:iewjuc34kzhytnytaxgknj6s5a

A Survey of Content-Aware Video Analysis for Sports

Huang-Chia Shih
2018 IEEE transactions on circuits and systems for video technology (Print)  
On the basis of this insight, we provide an overview of the themes particularly relevant to the research on content-aware systems for broadcast sports.  ...  Sports data analysis is becoming increasingly large-scale, diversified, and shared, but difficulty persists in rapidly accessing the most crucial information.  ...  In this approach, a set of overcomplete ICA basis functions is learned from 3D patches from training videos for each action.  ... 
doi:10.1109/tcsvt.2017.2655624 fatcat:rwqzu46sgfb7tpkcav4ysmh6ae

Hyperspectral Image Classification [chapter]

Rajesh Gogineni, Ashvini Chaturvedi
2019 Processing and Analysis of Hyperspectral Data [Working Title]  
This chapter discusses the recent progress in the classification of HS images in the aspects of Kernel-based methods, supervised and unsupervised classifiers, classification based on sparse representation  ...  In the field of remote sensing, HSI classification has been an established research topic, and herein, the inherent primary challenges are (i) curse of dimensionality and (ii) insufficient samples pool  ...  been investigated in recent years for the identification or classification of hyperspectral data.  ... 
doi:10.5772/intechopen.88925 fatcat:7ixv44bobbd3vkp7hn5c6tlb2y

Pattern recognition: Historical perspective and future directions

Azriel Rosenfeld, Harry Wechsler
2000 International journal of imaging systems and technology (Print)  
In this framework, data representation requires the specification of a basis set of approximating functions.  ...  using "natural" bases, and the use of mixtures of experts in classification.  ...  There is a wide range of opinions on the utility of artificial neural networks (ANNs) for statistical inference.  ... 
doi:10.1002/1098-1098(2000)11:2<101::aid-ima1>3.0.co;2-j fatcat:7avx2v64l5h6leyn5pdgg6s4ey

Neural correlates of sparse coding and dimensionality reduction

Michael Beyeler, Emily L. Rounds, Kristofor D. Carlson, Nikil Dutt, Jeffrey L. Krichmar, Aldo A. Faisal
2019 PLoS Computational Biology  
Although NSC might not apply to all brain areas (for example, motor or executive function areas) the success of NSC-based models, especially in sensory areas, warrants further investigation for neural  ...  In addition, NSC might provide a useful theoretical framework under which to understand the often complex and nonintuitive response properties of neurons in other brain areas.  ...  Analogously to [35, 37] , the basis functions obtained in NSC can be interpreted as the connection weights of a population of simulated neurons in an artificial neural network.  ... 
doi:10.1371/journal.pcbi.1006908 pmid:31246948 pmcid:PMC6597036 fatcat:llm2wwvr6jdlphqgjx6gt7ikv4

Neighbouring Proximity - An Key Impact Factor of Deep Machine Learning

Hongyuan Shi, Yunke Li, Liang Chen, Fan Jiang
2018 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)  
It has an outstanding capability to extract and represent the features of raw data and it has been applied to many domains, such as image processing, pattern recognition, computer vision, machine translation  ...  While the advantages of deep learning methods are widely accepted, the limitations are not well studied.  ...  Sparse Coding Sparse coding is a typical unsupervised dictionary learning method designed to learn a dictionary consist of overcomplete bases to represent data.  ... 
doi:10.1109/icci-cc.2018.8482089 dblp:conf/IEEEicci/ShiLCJ18 fatcat:t7misysu3bdhjgbx2uwnbrshf4

A Hierarchical Statistical Model of Natural Images Explains Tuning Properties in V2

H. Hosoya, A. Hyvarinen
2015 Journal of Neuroscience  
Further, a formal classification of the internal representations of the model units offered detailed interpretations of the experimental data, emphasizing that a novel type of model cell that could detect  ...  To address this question for V2, we trained a sparse coding model that took as input the output of a fixed V1-like model, which was in its turn fed a large variety of natural image patches as input.  ...  Sparse coding theory offers a candidate for such an encoding strategy, in which a network is adapted so that inputs are represented by a small number of neural activities.  ... 
doi:10.1523/jneurosci.5152-14.2015 pmid:26203137 fatcat:sr4gou3llncdzhl7hdnf2f2xq4

Machine learning in acoustics: theory and applications [article]

Michael J. Bianco, Peter Gerstoft, James Traer, Emma Ozanich, Marie A. Roch, Sharon Gannot, Charles-Alban Deledalle
2019 arXiv   pre-print
ML is a broad family of techniques, which are often based in statistics, for automatically detecting and utilizing patterns in data.  ...  We survey the recent advances and transformative potential of machine learning (ML), including deep learning, in the field of acoustics.  ...  ACKNOWLEDGMENTS This work was supported by the Office of Naval Research, Grant No. N00014-18-1-2118.  ... 
arXiv:1905.04418v3 fatcat:xuhykqhrk5bqbg5x7gaajcksay

27th Annual Computational Neuroscience Meeting (CNS*2018): Part Two

2018 BMC Neuroscience  
P271 Predicting runway excitation in nonlinear Hawkes processes  ...  Acknowledgements Ensemble modeling was performed on the Neuroscience Gateway Portal [4]. This work is supported by the CMBC Interdisciplinary Neuroscience Pilot Research Fund at Emory University.  ...  We believe that these synapse models would allow us to better understand the neural basis of visual perception. The following points should be underscored.  ... 
doi:10.1186/s12868-018-0451-y fatcat:afgrjlnjgjarldkuwo3e2pt5sm

Fault Detection in a Wind Turbine Hydraulic Pitch System Using Deep Autoencoder Extracted Features

Panagiotis Korkos, Jaakko Kleemola, Matti Linjama, Arto Lehtovaara
2022 Proceedings of the European Conference of the Prognostics and Health Management Society (PHME)  
In this study, a feature space of 49 features is available, referring to the condition of a hydraulic pitch system.  ...  The data are acquired from a wind farm of five 2.3MW fixed-speed wind turbines. The performance metric used to evaluate their effect on data is F1-score.  ...  Neural Networks.  ... 
doi:10.36001/phme.2022.v7i1.3330 fatcat:zndadp2umjh5na5zogmwqjpura

The Potential of Machine Learning for a More Responsible Sourcing of Critical Raw Materials

Pedram Ghamisi, Kasra Rafiezadeh Shahi, Puhong Duan, Behnood Rasti, Sandra Lorenz, Rene Booysen, Samuel Thiele, Isabel Cecilia Contreras Acosta, Moritz Kirsch, Richard Gloaguen
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this review, we assess the relevant recent developments of Machine Learning for the processing of imaging sensor data.  ...  We first describe the main imagers and the acquired data types as well as the platforms on which they can be installed.  ...  Furthermore, the kernel operations that form the basis of many modern approaches to image classification (e.g., convolutional neural networks) cannot be directly translated to unstructured data.  ... 
doi:10.1109/jstars.2021.3108049 fatcat:dopyzl427rhmbi7nejpug7ahfq
« Previous Showing results 1 — 15 out of 133 results