13.3.9.2 Boltzmann Machine, Simulated Annealing, and Related Topics

Kirpatrick, S., Gelatt, Jr., C.D., and Vecchi, M.P.,
Optimization by Simulated Annealing,
Science(220), 13 May 1983, pp. 671-680. Iterative optimization method that is described in terms used in cooling metal. Reducing the energy level slowly to go to some reduced energy state, resetting the state by random events, etc. BibRef 8305

Geman, S., and Geman, D.,
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images,
PAMI(6), No. 6, November 1984, pp. 721-741.
PDF File. BibRef 8411

Ackley, D.H., Hinton, G.E., and Sejnowski, T.J.,
A Learning Algorithm for Boltzmann Machines,
CogSci(9), 1985, pp. 147-169. Reprinted: BibRef 8500 RCV87(522-533). The massively parallel, simple processing element description of the relaxation process. BibRef

Hinton, G.E.[Geoffrey E.], and Sejnowski, T.J.[Terrence J.],
Optimal Perceptual Inference,
CVPR83(448-453). Different formulation of probabilistic relaxation and how to avoid non global minima (energy states). BibRef 8300

Sejnowski, T.J., and Hinton, G.E.,
Separating Figure from Ground with a Boltzmann Machine,
VBCC1987. BibRef 8700

Dyan, P., Hinton, G.E., Neal, R.M., and Zemel, R.S.,
The Helmholtz Machine,
NeurComp(7), No. 7, 1995, pp. 889-904. BibRef 9500

Tang, Y.C.[Yi-Chuan], Salakhutdinov, R.[Ruslan], Hinton, G.E.[Geoffrey E.],
Robust Boltzmann Machines for recognition and denoising,
CVPR12(2264-2271).
IEEE DOI 1208
BibRef

Carnevali, P., Coletti, L., Patarnello, S.,
Image Processing by Simulated Annealing,
IBMRD(29), No. 6, November 1985, pp. 569-579. BibRef 8511

Szu, H.H., Hartley, R.L.,
Nonconvex Optimization by Fast Simulated Annealing,
PIEEE(75), 1987, pp. 1538-1540. BibRef 8700

Klein, R.W.[Raymond W.], Dubes, R.C.[Richard C.],
Experiments in projection and clustering by simulated annealing,
PR(22), No. 2, 1989, pp. 213-220.
Elsevier DOI 0309
BibRef

Li, X.B.[Xiao-Bo], Dubes, R.C.[Richard C.],
A probabilistic measure of similarity for binary data in pattern recognition,
PR(22), No. 4, 1989, pp. 397-409.
Elsevier DOI 0309
BibRef

Atkin, G.K., Bowcock, J.E., Queen, N.M.,
Solution of a distributed deterministic parallel network using simulated annealing,
PR(22), No. 4, 1989, pp. 461-466.
Elsevier DOI 0309
BibRef

Selim, S.Z.[Shokri Z.], Alsultan, K.,
A simulated annealing algorithm for the clustering problem,
PR(24), No. 10, 1991, pp. 1003-1008.
Elsevier DOI 0401
BibRef

Brown, D.E.[Donald E.], Huntley, C.L.[Christopher L.],
A practical application of simulated annealing to clustering,
PR(25), No. 4, April 1992, pp. 401-412.
Elsevier DOI 0401
BibRef

d'Anjou, A., Grana, M., Torrealdea, F.J., and Hernandez, M.C.,
Solving Satisfiability via Boltzmann Machines,
PAMI(15), No. 5, May 1993, pp. 514-521.
IEEE DOI BibRef 9305

Granville, V., Krivanek, M., Rasson, J.P.,
Simulated Annealing: A Proof of Convergence,
PAMI(16), No. 6, June 1994, pp. 652-656.
IEEE DOI BibRef 9406

Storvik, G.,
A Bayesian-Approach to Dynamic Contours Through Stochastic Sampling and Simulated Annealing,
PAMI(16), No. 10, October 1994, pp. 976-986.
IEEE DOI BibRef 9410

Bongiovanni, G., Crescenzi, P., Guerra, C.,
Parallel Simulated Annealing for Shape Detection,
CVIU(61), No. 1, January 1995, pp. 60-69.
DOI Link BibRef 9501

Guerra, C.,
Survey of parallel algorithms for structural pattern matching,
ICPR94(C:275-278).
IEEE DOI 9410
BibRef

Li, S.Z.,
Robustizing Robust M-Estimation Using Deterministic Annealing,
PR(29), No. 1, January 1996, pp. 159-166.
Elsevier DOI BibRef 9601

Taxt, T.[Torfinn], Bølviken, E.[Erik],
Relaxation Using Models from Quantum Mechanics,
PR(24), No. 7, 1991, pp. 695-709.
Elsevier DOI BibRef 9100

Albizuri, F.X., d'Anjou, A., Grana, M., Lozano, J.A.,
Convergence Properties of High-Order Boltzmann Machines,
NeurNet(9), No. 9, December 1996, pp. 1561-1567. 9701
BibRef

Aleksander, I.,
Adaptive Pattern Recognition Systems and Boltzmann Machines: A Rapprochement,
PRL(6), 1987, pp. 113-120. BibRef 8700

Barhen, J.[Jacob], Protopopescu, V.[Vladimir], Reister, D.B.[David B.],
TRUST: A Deterministic Algorithm for Global Optimization,
Science(276), No. 5315, 16 May 1997, pp. 1094-1097. Global optimization that is faster and more accurate and escapes local minima. BibRef 9705

Noll, D.[Detlev], von Seelen, W.[Werner],
Object Recognition by Deterministic Annealing,
IVC(15), No. 11, November 1997, pp. 855-860.
Elsevier DOI 9712
BibRef

Noll, D., Schwarzinger, M., von Seelen, W.,
Contextual feature similarities for model-based object recognition,
ICCV93(286-290).
IEEE DOI 0403
BibRef

Kappen, H.J., Rodriguez, F.B.,
Mean-Field Approach to Learning in Boltzmann Machines,
PRL(18), No. 11-13, November 1997, pp. 1317-1322. 9806
BibRef

Rao, A.V.[Ajit V.], Miller, D.J.[David J.], Rose, K.[Kenneth], Gersho, A.[Allen],
A Deterministic Annealing Approach for Parsimonious Design of Piecewise Regression Models,
PAMI(21), No. 2, February 1999, pp. 159-173.
IEEE DOI BibRef 9902

Rangarajan, A.[Anand],
Self-annealing and self-annihilation: unifying deterministic annealing and relaxation labeling,
PR(33), No. 4, April 2000, pp. 635-649.
Elsevier DOI 0002
BibRef

Klock, H.J.[Hans-Jörg], Buhmann, J.M.[Joachim M.],
Data Visualization by Multidimensional Scaling: A Deterministic Annealing Approach,
PR(33), No. 4, April 2000, pp. 651-669.
Elsevier DOI 0002
BibRef

Chen, H., Murray, A.F.,
Continuous restricted Boltzmann machine with an implementable training algorithm,
VISP(150), No. 3, June 2003, pp. 153-158.
IEEE Abstract. 0308
BibRef

Thompson, D.R., Bilbro, G.L.,
Sample-Sort Simulated Annealing,
SMC-B(35), No. 3, June 2005, pp. 625-632.
IEEE DOI 0508
BibRef

Luo, Q.A.[Qi-Ang], Yang, W.Q.[Wen-Qiang], Liu, P.Y.[Pu-Yin],
Promoter recognition based on the Interpolated Markov Chains optimized via simulated annealing and genetic algorithm,
PRL(27), No. 9, July 2006, pp. 1031-1036.
Elsevier DOI Simulated annealing 0605
BibRef

Yang, X.L., Song, Q., Zhang, W.B.,
Kernel-based deterministic annealing algorithm for data clustering,
VISP(153), No. 5, October 2006, pp. 557-568.
DOI Link 0702
BibRef

Ma, J.W.[Jin-Wen], Liu, J.F.[Jian-Feng],
The BYY annealing learning algorithm for Gaussian mixture with automated model selection,
PR(40), No. 7, July 2007, pp. 2029-2037.
Elsevier DOI 0704
Bayesian Ying-Yang (BYY) learning; Gaussian mixture; Automated model selection; Simulated annealing; Unsupervised image segmentation BibRef

Ma, J.W.[Jin-Wen], Liu, J.F.[Jian-Feng], Ren, Z.J.[Zhi-Jie],
Parameter estimation of Poisson mixture with automated model selection through BYY harmony learning,
PR(42), No. 11, November 2009, pp. 2659-2670.
Elsevier DOI 0907
Bayesian Ying-Yang (BYY) harmony learning; Poisson mixture; Gradient learning algorithm; Automated model selection; Texture classification BibRef

Ma, J.W.[Jin-Wen], He, X.F.[Xue-Feng],
A fast fixed-point BYY harmony learning algorithm on Gaussian mixture with automated model selection,
PRL(29), No. 6, 15 April 2008, pp. 701-711.
Elsevier DOI 0803
Bayesian Ying-Yang (BYY) system; Harmony learning; Gaussian mixture; Automated model selection; Fixed-point BibRef

Gall, J.[Jürgen], Potthoff, J.[Jürgen], Schnörr, C.[Christoph], Rosenhahn, B.[Bodo], Seidel, H.P.[Hans-Peter],
Interacting and Annealing Particle Filters: Mathematics and a Recipe for Applications,
JMIV(28), No. 1, May 2007, pp. 1-18.
Springer DOI 0710
BibRef

Gall, J.[Juergen], Rosenhahn, B.[Bodo], Seidel, H.P.[Hans-Peter],
Drift-free tracking of rigid and articulated objects,
CVPR08(1-8).
IEEE DOI 0806
BibRef
Earlier:
Clustered Stochastic Optimization for Object Recognition and Pose Estimation,
DAGM07(32-41).
Springer DOI 0709
Award, GCPR. BibRef
Earlier:
Robust Pose Estimation with 3D Textured Models,
PSIVT06(84-95).
Springer DOI 0612
BibRef

Gedeon, T.[Tomas], Parker, A.E.[Albert E.], Campion, C.[Collette], Aldworth, Z.[Zane],
Annealing and the normalized N-cut,
PR(41), No. 2, February 2008, pp. 592-606.
Elsevier DOI 0711
Clustering; Annealing; Normalized N-cut BibRef

Saha, S.[Sriparna], Bandyopadhyay, S.[Sanghamitra],
A symmetry based multiobjective clustering technique for automatic evolution of clusters,
PR(43), No. 3, March 2010, pp. 738-751.
Elsevier DOI 1001
BibRef
Earlier:
A new multiobjective simulated annealing based clustering technique using stability and symmetry,
ICPR08(1-4).
IEEE DOI 0812
BibRef
And:
A multiobjective simulated annealing based fuzzy-clustering technique with symmetry for pixel classification in remote sensing imagery,
ICPR08(1-4).
IEEE DOI 0812
Clustering; Multiobjective optimization (MOO); Symmetry; Point symmetry based distance; Cluster validity index; Simulated annealing (SA)
See also GAPS: A clustering method using a new point symmetry-based distance measure. BibRef

Xavier-de-Souza, S., Suykens, J.A.K., Vandewalle, J., Bolle, D.,
Coupled Simulated Annealing,
SMC-B(40), No. 2, April 2010, pp. 320-335.
IEEE DOI 1003
BibRef

Zhang, Z.H.[Zhi-Hua], Wang, G.[Gang], Yeung, D.Y.[Dit-Yan], Dai, G.[Guang], Lochovsky, F.[Frederick],
A regularization framework for multiclass classification: A deterministic annealing approach,
PR(43), No. 7, July 2010, pp. 2466-2475.
Elsevier DOI 1003
Multiclass classification; Deterministic annealing; Maximum entropy; Fisher discriminant analysis; Logistic regression BibRef

Park, B.G.[Bo Gun], Lee, K.M.[Kyoung Mu], Lee, S.U.[Sang Uk], Lee, J.H.[Jin Hak],
Recognition of partially occluded objects using probabilistic ARG-based matching,
CVIU(90), No. 3, June 2003, pp. 217-241.
Elsevier DOI 0307
Attributed Relational Graph BibRef

Park, B.G.[Bo Gun], Lee, K.M.[Kyoung Mu], Lee, S.U.[Sang Uk],
A Novel Stochastic Attributed Relational Graph Matching Based on Relation Vector Space Analysis,
ACIVS06(978-989).
Springer DOI 0609
BibRef

Jung, H.Y.[Ho Yub], Lee, K.M.[Kyoung Mu], Lee, S.U.[Sang Uk],
Window annealing for pixel-labeling problems,
CVIU(117), No. 3, March 2013, pp. 289-303.
Elsevier DOI 1302
BibRef
Earlier:
Window Annealing over Square Lattice Markov Random Field,
ECCV08(II: 307-320).
Springer DOI 0810
BibRef
And:
Toward Global Minimum through Combined Local Minima,
ECCV08(IV: 298-311).
Springer DOI 0810
Energy minimization; Simulated annealing; Markov chain Monte Carlo; Markov random fields; Sequential Monte Carlo; Heuristic optimization; Pixel labeling problems BibRef

Campaigne, W.R., Fieguth, P.W.,
Frozen-State Hierarchical Annealing,
IP(22), No. 4, April 2013, pp. 1486-1497.
IEEE DOI 1303
BibRef

Campaigne, W.R.[Wesley R.], Fieguth, P.W.[Paul W.], Alexander, S.K.[Simon K.],
Frozen-State Hierarchical Annealing,
ICIAR06(I: 41-52).
Springer DOI 0610
BibRef

Alexander, S.K., Fieguth, P.W., Vrscay, E.R.,
Image sampling by hierarchical annealing,
ICIP03(I: 249-252).
IEEE DOI 0312
BibRef

Jamieson, M., Fieguth, P.W., Lee, L.J.,
Parametric contour estimation by simulated annealing,
ICIP03(III: 449-452).
IEEE DOI 0312
BibRef

Fischer, A.[Asja], Igel, C.[Christian],
Training restricted Boltzmann machines: An introduction,
PR(47), No. 1, 2014, pp. 25-39.
Elsevier DOI 1310
Award, Pattern Recognition. Restricted Boltzmann machines BibRef

Nie, S.Q.[Si-Qi], Wang, Z.H.[Zi-Heng], Ji, Q.A.[Qi-Ang],
A generative restricted Boltzmann machine based method for high-dimensional motion data modeling,
CVIU(136), No. 1, 2015, pp. 14-22.
Elsevier DOI 1506
Restricted Boltzmann machine BibRef

Lee, H.J.[Hui-Jin], Hong, K.S.[Ki-Sang],
Class-specific mid-level feature learning with the Discriminative Group-wise Beta-Bernoulli process restricted Boltzmann machines,
PRL(80), No. 1, 2016, pp. 8-14.
Elsevier DOI 1609
Mid-level feature BibRef

Sankaran, A.[Anush], Goswami, G.[Gaurav], Vatsa, M.[Mayank], Singh, R.[Richa], Majumdar, A.[Angshul],
Class sparsity signature based Restricted Boltzmann Machine,
PR(61), No. 1, 2017, pp. 674-685.
Elsevier DOI 1705
Deep learning BibRef

Yan, J., Li, C., Li, Y., Cao, G.,
Adaptive Discrete Hypergraph Matching,
Cyber(48), No. 2, February 2018, pp. 765-779.
IEEE DOI 1801
Annealing, Complexity theory, Convergence, Cybernetics, Iterative methods, Optimization, Tensile stress, pattern recognition BibRef

Krause, O.[Oswin], Fischer, A.[Asja], Igel, C.[Christian],
Population-Contrastive-Divergence: Does consistency help with RBM training?,
PRL(102), 2018, pp. 1-7.
Elsevier DOI 1802
Restricted Boltzmann machine, Markov chain Monte Carlo, Contrastive divergence, Population Monte Carlo BibRef

Nakashika, T.[Toru],
Deep Relational Model: A Joint Probabilistic Model with a Hierarchical Structure for Bidirectional Estimation of Image and Labels,
IEICE(E101-D), No. 2, February 2018, pp. 428-436.
WWW Link. 1802
BibRef

Giuffrida, M.V., Tsaftaris, S.A.,
Unsupervised Rotation Factorization in Restricted Boltzmann Machines,
IP(29), 2020, pp. 2166-2175.
IEEE DOI 2001
Training, Neural networks, Image reconstruction, Feature extraction, Mathematical model, Image representation, restricted Boltzmann machines BibRef

Lee, J.[Julian], Perkins, D.[David],
A simulated annealing algorithm with a dual perturbation method for clustering,
PR(112), 2021, pp. 107713.
Elsevier DOI 2102
Partitional clustering, Simulated annealing, Sum of squared error criterion, -means BibRef

Li, W.[Wanyi], Zeng, Y.Q.[Yu-Qi], Wu, Y.[Yilin], Zhang, Q.[Qian], Chen, G.M.[Guo-Ming], Chen, Y.C.[Yong-Chang],
Dynamic manifold Boltzmann optimization based on self-supervised learning for human motion estimation,
IET-IPR(16), No. 4, 2022, pp. 1162-1180.
DOI Link 2203
BibRef

Zhang, N.[Nan], Sun, S.L.[Shi-Liang],
Multiview Graph Restricted Boltzmann Machines,
Cyber(52), No. 11, November 2022, pp. 12414-12428.
IEEE DOI 2211
Data models, Manifolds, Training, Adaptation models, Computational modeling, Bayes methods, Sun, Graph learning, restricted Boltzmann machines (RBM) BibRef

Kanno, Y.[Yuri], Yasuda, M.[Muneki],
Multi-layered Discriminative Restricted Boltzmann Machine with Untrained Probabilistic Layer,
ICPR21(7655-7660)
IEEE DOI 2105
Training, Extreme learning machines, Neural networks, Stacking, Benchmark testing, Probabilistic logic BibRef

Holzschuh, B., Lähner, Z., Cremers, D.,
Simulated Annealing for 3D Shape Correspondence,
3DV20(252-260)
IEEE DOI 2102
Shape, Simulated annealing, Optimization, Generators, Impedance matching, Probabilistic logic, Locality Sensitive Hashing BibRef

Oussidi, A., Elhassouny, A.,
Deep generative models: Survey,
ISCV18(1-8)
IEEE DOI 1807
Boltzmann machines, belief networks, learning (artificial intelligence), recurrent neural nets, DRAW, Training BibRef

Júnior, L.A.P.[Leandro A. Passos], Costa, K.A.P.[Kelton A. P.], Papa, J.P.[João P.],
Deep Boltzmann Machines Using Adaptive Temperatures,
CAIP17(I: 172-183).
Springer DOI 1708
BibRef

Dasgupta, S., Yoshizumi, T., Osogami, T.,
Regularized dynamic Boltzmann machine with Delay Pruning for unsupervised learning of temporal sequences,
ICPR16(1201-1206)
IEEE DOI 1705
Artificial neural networks, Biological neural networks, Delays, History, Neurons, Training, Unsupervised, learning BibRef

Wang, J.J.[Jian-Jia], Wilson, R.C.[Richard C.], Hancock, E.R.[Edwin R.],
Network Edge Entropy from Maxwell-Boltzmann Statistics,
CIAP17(I:254-264).
Springer DOI 1711
BibRef
Earlier:
Network entropy analysis using the Maxwell-Boltzmann partition function,
ICPR16(1321-1326)
IEEE DOI 1705
BibRef
And:
Thermodynamic Network Analysis with Quantum Spin Statistics,
SSSPR16(153-162).
Springer DOI 1611
Data models, Energy states, Entropy, Heating systems, Laplace equations, Numerical models, Thermodynamics
See also Minimising Entropy Changes in Dynamic Network Evolution.
See also Quantum Edge Entropy for Alzheimer's Disease Analysis. BibRef

Gu, L.Y.[Lin-Yan], Yang, L.H.[Li-Hua],
On the magnitude of parameters of RBMs being universal approximators,
ICPR16(2470-2474)
IEEE DOI 1705
Approximation algorithms, Computational modeling, Geometry, Markov processes, Mathematical model, Probability distribution, Visualization, bound of parameters, representation power, restricted, Boltzmann, machine BibRef

Yogeswaran, A.[Arjun], Payeur, P.[Pierre],
Improving Visual Feature Representations by Biasing Restricted Boltzmann Machines with Gaussian Filters,
ISVC16(I: 825-835).
Springer DOI 1701
BibRef

Baqué, P.[Pierre], Bagautdinov, T.[Timur], Fleuret, F.[François], Fua, P.[Pascal],
Principled Parallel Mean-Field Inference for Discrete Random Fields,
CVPR16(5848-5857)
IEEE DOI 1612
BibRef

Wang, J.Z.[Jin-Zhuo], Wang, W.M.[Wen-Min], Wang, R.G.[Rong-Gang], Gao, W.[Wen],
Image classification using RBM to encode local descriptors with group sparse learning,
ICIP15(912-916)
IEEE DOI 1512
Feature Coding Restricted Boltzmann Machines. BibRef

Sawada, Y.[Yoshihide], Kozuka, K.[Kazuki],
Transfer learning method using multi-prediction deep Boltzmann machines for a small scale dataset,
MVA15(110-113)
IEEE DOI 1507
Biomedical imaging BibRef

Barshan, E.[Elnaz], Fieguth, P.W.[Paul W.],
Scalable learning for restricted Boltzmann machines,
ICIP14(2754-2758)
IEEE DOI 1502
Computational modeling BibRef

Zhang, C.[Chao], Li, X.[Xiong], Yan, J.C.[Jun-Chi], Qui, S.[Stephen], Wang, Y.[Yu], Tian, C.H.[Chun-Hua], Zhao, Y.M.[Yu-Ming],
Sufficient Statistics Feature Mapping over Deep Boltzmann Machine for Detection,
ICPR14(827-832)
IEEE DOI 1412
Business BibRef

Yamashita, T.[Takayoshi], Tanaka, M.[Masayuki], Yoshida, E.[Eiji], Yamauchi, Y.[Yuji], Fujiyoshii, H.[Hironobu],
To Be Bernoulli or to Be Gaussian, for a Restricted Boltzmann Machine,
ICPR14(1520-1525)
IEEE DOI 1412
Data models BibRef

Tanaka, M.[Masayuki], Okutomi, M.[Masatoshi],
A Novel Inference of a Restricted Boltzmann Machine,
ICPR14(1526-1531)
IEEE DOI 1412
Approximation methods BibRef

Moreno, R.[Rodrigo], Smedby, O.[Orjan],
Volume-Based Fabric Tensors through Lattice-Boltzmann Simulations,
ICPR14(3179-3184)
IEEE DOI 1412
Anisotropic magnetoresistance BibRef

Yasuda, M.[Muneki],
Effective Mean-Field Inference Method for Nonnegative Boltzmann Machines,
ICPR14(3600-3605)
IEEE DOI 1412
Approximation methods BibRef

Mittelman, R.[Roni], Lee, H.L.[Hong-Lak], Kuipers, B.[Benjamin], Savarese, S.[Silvio],
Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines,
CVPR13(476-483)
IEEE DOI 1309
Beta-Bernoulli process BibRef

Yasuda, M.[Muneki], Kataoka, S.[Shun], Waizumi, Y.[Yuji], Tanaka, K.[Kazuyuki],
Composite likelihood estimation for restricted Boltzmann machines,
ICPR12(2234-2237).
WWW Link. 1302
BibRef

Lopes, N.[Noel], Ribeiro, B.[Bernardete],
Improving Convergence of Restricted Boltzmann Machines via a Learning Adaptive Step Size,
CIARP12(511-518).
Springer DOI 1209
BibRef

Fischer, A.[Asja], Igel, C.[Christian],
An Introduction to Restricted Boltzmann Machines,
CIARP12(14-36).
Springer DOI 1209
BibRef

Papandreou, G.[George], Chen, L.C.[Liang-Chieh], Yuille, A.L.[Alan L.],
Modeling Image Patches with a Generic Dictionary of Mini-epitomes,
CVPR14(2059-2066)
IEEE DOI 1409
BibRef
Earlier: A2, A1, A3:
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling,
ICCV13(337-344)
IEEE DOI 1403
Image classification; epitomes; image patches. Local edge structure, shifts, rotations. BibRef

Papandreou, G.[George], Yuille, A.L.[Alan L.],
Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models,
ICCV11(193-200).
IEEE DOI 1201
Add noise, then find glabal minimum of pertrubed field. BibRef

Goh, H.L.[Han-Lin], Thome, N.[Nicolas], Cord, M.[Matthieu], Lim, J.H.[Joo-Hwee],
Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines,
ECCV12(V: 298-311).
Springer DOI 1210
BibRef

Goh, H.L.[Han-Lin], Kusmierz, L.[Lukasz], Lim, J.H.[Joo-Hwee], Thome, N.[Nicolas], Cord, M.[Matthieu],
Learning invariant color features with sparse topographic restricted Boltzmann machines,
ICIP11(1241-1244).
IEEE DOI 1201
BibRef

Norouzi, M.[Mohammad], Ranjbar, M.[Mani], Mori, G.[Greg],
Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning,
CVPR09(2735-2742).
IEEE DOI 0906
BibRef

Portilla, J.[Javier],
Image restoration through L0 analysis-based sparse optimization in tight frames,
ICIP09(3909-3912).
IEEE DOI 0911
BibRef

Mancera, L.[Luis], Portilla, J.[Javier],
Non-convex sparse optimization through deterministic annealing and applications,
ICIP08(917-920).
IEEE DOI 0810
BibRef

Mohebi, A.[Azadeh], Liu, Y.[Ying], Fieguth, P.W.[Paul W.],
Hierarchical Sampling with Constraints,
ICIAR09(23-32).
Springer DOI 0907
BibRef
Earlier: A1, A3, Only:
Constrained Sampling Using Simulated Annealing,
ICIAR07(198-209).
Springer DOI 0708
BibRef

Mohebi, A.[Azadeh], Fieguth, P.W.[Paul W.],
Posterior Sampling of Scientific Images,
ICIAR06(I: 339-350).
Springer DOI 0610
in MRI, infer structures as scales not imaged by the MRI. BibRef

Sun, L.Y.[Ling-Yu], Leng, M.[Ming],
An Effective Multi-level Algorithm Based on Simulated Annealing for Bisecting Graph,
EMMCVPR07(1-12).
Springer DOI 0708
BibRef

Yang, X.L.[Xu-Lei], Song, Q.[Qing], Zhang, W.B.[Wen-Bo], Wang, Z.M.[Zhi-Min],
Clustering Spherical Shells by a Mini-Max Information Algorithm,
ACCV06(II:224-233).
Springer DOI 0601
BibRef

Perrin, G.[Guillaume], Descombes, X.[Xavier], Zerubia, J.B.[Josiane B.],
Adaptive Simulated Annealing for Energy Minimization Problem in a Marked Point Process Application,
EMMCVPR05(3-17).
Springer DOI 0601
BibRef

Ortner, M.[Mathias], Descombes, X.[Xavier], Zerubia, J.B.[Josiane B.],
Improved RJMCMC point process sampler for object detection on images by simulated annealing,
INRIARR-4900, 2003.
HTML Version. BibRef 0300

Alexander, S.K.[Simon K.], Fieguth, P.W.[Paul W.], Vrscay, E.R.[Edward R.],
Parameterized Hierarchical Annealing for Scientific Models,
ICIAR04(I: 236-243).
Springer DOI 0409
BibRef

Hirano, T., Okada, Y., Yoda, F.,
Structural Character Recognition Using Simulated Annealing,
ICDAR97(507-510).
IEEE DOI 9708
BibRef

Younes, L.,
Learning algorithms for extended models of Boltzmann machines,
ICPR94(B:602-604).
IEEE DOI 9410
BibRef

Matsunaga, T., Kida, H.,
A method for designing dictionary using simulated annealing,
ICPR92(II:154-187).
IEEE DOI 9208
BibRef

Herault, L., Horaud, R., Veillon, F., Niez, J.J.,
Symbolic Image Matching by Simulated Annealing,
BMVC90(319-324).
PDF File. BibRef 9000

Xu, L.[Lei],
Some applications of simulated annealing to pattern recognition,
ICPR88(II: 1040-1042).
IEEE DOI 8811
BibRef

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
Hummel and Zucker Relaxation Papers .