Filters








71,200 Hits in 6.1 sec

Self-Organizing Map Learning with Momentum

Huang-Cheng Kuo, Shih-Hao Chen
2016 Computer and Information Science  
<p class="zhengwen"><span lang="EN-GB">Self-organizing map (SOM) is a type of artificial neural network for cluster analysis.  ...  Since self-organizing map may be trapped in a local optimum, so we introduce momentum into the learning process thus the movement of a neuron may jump over local optimum.  ...  Self-organizing map (Kohonen, 1982) is a competitive learning based clustering neural networks. Neurons on the map compete with each other for each input data.  ... 
doi:10.5539/cis.v9n1p136 fatcat:4ary5rl74railm3bljv4jccab4

CSAL: Self-adaptive Labeling based Clustering Integrating Supervised Learning on Unlabeled Data [article]

Fangfang Li, Guandong Xu, Longbing Cao
2015 arXiv   pre-print
In this paper, we propose an innovative and effective clustering framework based on self-adaptive labeling (CSAL) which integrates clustering and classification on unlabeled data.  ...  Experiments are conducted on publicly data sets to test different combinations of clustering algorithms and classification models as well as various training data labeling methods.  ...  [17] also introduced an algorithm for learning from labeled and unlabeled documents based on the combination of EM and a Naive Bayes classifier.  ... 
arXiv:1502.05111v1 fatcat:fgrd2zmivbbtlknngdiviuln5m

Self-supervised Deep Subspace Clustering for Hyperspectral Images with Adaptive Self-expressive Coefficient Matrix Initialization

Kun Li, Yao Qin, Qiang Ling, Yingqian Wang, Zaiping Lin, Wei An
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Index Terms-Deep subspace clustering (DSC), hyperspectral image (HSI), self-expressive, self-supervised, subspace clustering (SC).  ...  Then, an adaptive self-expressive coefficient matrix initialization strategy is designed to reduce the dictionary redundancy, where the spectral similarity between each target sample and its neighbors  ...  initialization module is used to provide a good initialized self-expressive coefficient matrix for the self-expressiveness module; d) self-supervised learning-based classification module classifies the  ... 
doi:10.1109/jstars.2021.3063335 fatcat:llkh4sqw7nblrpsbdk7ooe7d3i

Learning Deep Representation with Energy-Based Self-Expressiveness for Subspace Clustering [article]

Yanming Li, Changsheng Li, Shiye Wang, Ye Yuan, Guoren Wang
2022 arXiv   pre-print
In contrast to previous approaches taking the weights of a fully connected layer as the self-expressive coefficients, we propose to learn an energy-based network to obtain the self-expressive coefficients  ...  In this paper, we propose a new deep subspace clustering framework, motivated by the energy-based models.  ...  Finally, we approximate the representation z A i using the dictionary Z B and the learned self-expressive coefficients c i where is inner-product operation coefficient learning module based on energy based  ... 
arXiv:2110.15037v2 fatcat:fri55joh7fdmpjxjtjkv32ogh4

K-Deep Simplex: Deep Manifold Learning via Local Dictionaries [article]

Pranay Tankala, Abiy Tasissa, James M. Murphy, Demba Ba
2021 arXiv   pre-print
Our approach learns local dictionaries that represent a data point with reconstruction coefficients supported on the probability simplex.  ...  The dictionaries are learned using algorithm unrolling, an increasingly popular technique for structured deep learning.  ...  Our Contributions The main contribution of our work is a novel manifold learning and clustering algorithm based on sparse self-representation that overcomes both of the obstacles described in the previous  ... 
arXiv:2012.02134v2 fatcat:jw7nfmtztra7hcg2nhj7457ucu

Classifying spatiotemporal object trajectories using unsupervised learning of basis function coefficients

Shehzad Khalid, Andrew Naftel
2005 Proceedings of the third ACM international workshop on Video surveillance & sensor networks - VSSN '05  
The coefficients of the basis functions are used as input feature vectors to a Self-Organising Map which can learn similarities between object trajectories in an unsupervised manner.  ...  This paper proposes a novel technique for clustering and classification of object trajectory-based video motion clips using spatiotemporal functional approximations.  ...  The system architecture and trajectory learning algorithm is presented in section 3 within the framework of a self-organising map.  ... 
doi:10.1145/1099396.1099404 fatcat:eshvy3oxgvhh5cpawf6rfhyqu4

Beyond Linear Subspace Clustering: A Comparative Study of Nonlinear Manifold Clustering Algorithms [article]

Maryam Abdolali, Nicolas Gillis
2021 arXiv   pre-print
The majority of the prominent subspace clustering algorithms rely on the representation of the data points as linear combinations of other data points, which is known as a self-expressive representation  ...  We introduce a new taxonomy to classify the state-of-the-art approaches into three categories, namely locality preserving, kernel based, and neural network based.  ...  Conclusion In this paper, we presented a comprehensive overview of nonlinear subspace clustering (nonlinear SC) approaches, our main focus being on algorithms based on self-expressiveness.  ... 
arXiv:2103.10656v1 fatcat:vtlb3d337fgixkumu5faidisrm

A Self-Learning Diagnosis Algorithm Based on Data Clustering

Dmitry Tretyakov
2016 Intelligent Control and Automation  
How to cite this paper: Tretyakov, D. (2016) A Self-Learning Diagnosis Algorithm Based on Data Clustering. Intelligent Control and Automation, 7, 84-92. http://dx.  ...  Abstract The article describes an approach to building a self-learning diagnostic algorithm. The self-learning algorithm creates models of the object under consideration.  ...  The diagnostic algorithm has to use the signals coming from sensors for self-learning. In [10] the learning methods based on association are used for generating new rules from incoming data.  ... 
doi:10.4236/ica.2016.73009 fatcat:cwnzxkeskvb7nck4obr7elrp3e

DSCD:A Novel Deep Subspace Clustering Denoise Network For Single-cell Clustering

Zhiye Wang, Yiwen Lu, Chang Yu, Tao Zhou, Ruiyi Li, Siyun Hou
2020 IEEE Access  
SPECTRAL CLUSTERING The spectral clustering algorithm is based on the spectral graph theory.  ...  NMF [30] is an algorithm for non-negative matrix factorization, which learns holistic, not parts-based, representations.  ... 
doi:10.1109/access.2020.3001986 fatcat:wexzgp6u4zek7n4uw57aavk6qe

Centroid neural network for unsupervised competitive learning

Dong-Chul Park
2000 IEEE Transactions on Neural Networks  
An unsupervised competitive learning algorithm based on the classical -means clustering algorithm is proposed.  ...  The CNN algorithm requires neither a predetermined schedule for learning coefficient nor a total number of iterations for clustering.  ...  CONCLUSION The CNN algorithm based on the -means clustering algorithm is proposed. The proposed CNN algorithm has a strong connection with some of the conventional unsupervised learning algorithms.  ... 
doi:10.1109/72.839021 pmid:18249781 fatcat:pyzhrl723zdahfxwtd3g57qj4u

Motion Trajectory Learning in the DFT-Coefficient Feature Space

A. Naftel, S. Khalid
2006 Fourth IEEE International Conference on Computer Vision Systems (ICVS'06)  
The DFT coefficients are used as input feature vectors to a Self-Organising Map which can learn similarities between object trajectories in an unsupervised manner.  ...  In this paper we propose a novel vision system for clustering and classification of object-based video motion clips using spatiotemporal models.  ...  The system architecture and trajectory learning algorithm is presented in section 3 within the framework of a self-organising map.  ... 
doi:10.1109/icvs.2006.41 dblp:conf/icvs/NaftelK06 fatcat:5o6rywvkebcx3cwlx7bnffisry

Limitations of Using Constraint Set Utility in Semi-Supervised Clustering

Toon van Craenendonck, Hendrik Blockeel
2015 European Conference on Principles of Data Mining and Knowledge Discovery  
We compare some of these algorithms experimentally, and observe that their performances vary significantly, depending on the data set and constraints.  ...  Semi-supervised clustering algorithms allow the user to incorporate background knowledge into the clustering process.  ...  For example, one can learn a separate metric for each cluster, or a global one.  ... 
dblp:conf/pkdd/CraenendonckB15 fatcat:5wfbst6x3rdpdgy7yhbjctasou

Towards Self-adaptive Defect Classification in Industrial Monitoring

Andreas Margraf, Jörg Hähner, Philipp Braml, Steffen Geinitz
2020 Proceedings of the 9th International Conference on Data Science, Technology and Applications  
We compare well-known heuristics, based on k-means, hierarchical-and density based clustering and configure them to work best under the given circumstances.  ...  We then cluster the incoming defect data with stream clustering algorithms in order to identify structures, tendencies and anomalies.  ...  In order to answer this question we propose a clustering based approach for unsupervised learning on a representative industrial image dataset.  ... 
doi:10.5220/0009893003180327 dblp:conf/data/MargrafHBG20 fatcat:c4nhum2okbed7nyjw6xm3u3jjy

Method of Image De-Noising Based on Non-Noisy Atoms Self Adaptive and Sparse Representation

Li Weizheng
2016 International Journal of Signal Processing, Image Processing and Pattern Recognition  
In allusion to the losses of image detail and texture structure information during image de-noising process, an image de-noising algorithm based on non-related dictionary learning is proposed in this paper  ...  Firstly, this algorithm is adopted to obtain selfadaption redundant dictionary for the noisy image through the dictionary learning algorithm; secondly, HOG features and gray-level statistical features  ...  In recent years, the de-noising method based on dictionary learning [1] [2] [3] [4] and the de-noising method based on nonlocal self-similarity [5] [6] [7] [8] in the image processing field are widely  ... 
doi:10.14257/ijsip.2016.9.8.35 fatcat:rzslafhndrhdhiwge7hxgy27re

Dynamic CR-based Classifiers Ensemble based on Multi-View Kernel Collaborative Subspace Clustering for Hyperspectral Image Classification

Hongliang Lu, Hongjun Su, Jun Hu, Qian Du
2022 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Moreover, a new method of constructing the Laplacian matrix using kernel CR coefficients is proposed for clustering based on subspace clustering and CR theory.  ...  This method is called MVKCSC, which can obtain the clustering results by using kernel CR self-representation coefficients.  ...  Subspace Clustering Based on Spectral Clustering The subspace clustering algorithm based on spectral clustering is one of the subspace clustering algorithms.  ... 
doi:10.1109/jstars.2022.3158761 fatcat:nopnupirovd4ji6canfoaaro2m
« Previous Showing results 1 — 15 out of 71,200 results