- In: Encyclopedia of Cognitive Science, Macmillan Publishers Ltd., 2002. URL: http://cns.georgetown.edu/~miguel/papers/ecs02.html
- Dimensionality reduction This chapter introduces and defines the problem of dimensionality reduction, discusses the topics of the curse
- Manifold Blurring Mean Shift Algorithms for Manifold Denoising Weiran Wang Miguel A. Carreira-Perpi~nan
- Articulatory CarreiraPerpi
- In: J. Neurophysiology 92(5):29472959 (Nov. 2004) URL: http://www.cse.ogi.edu/~miguel/papers.html
- The Geometry of the Articulatory Region That Produces a Speech Sound Chao Qin and Miguel
- A Review of Dimension Reduction Techniques \Lambda A. CarreiraPerpi~n'an
- KERNEL DENSITY ESTIMATION, AFFINITYBASED CLUSTERING, AND TYPICAL CUTS Deniz Erdo gmus Miguel
- Density Networks for Dimension Reduction of Continuous Data: Analytical Solutions
- On Contrastive Divergence Learning A. CarreiraPerpinan # Geo#rey E. Hinton
- A Computational Model for the Development of Multiple Maps in Primary Visual Cortex
- The Laplacian Eigenmaps Latent Variable Model A. CarreiraPerpinan Zhengdong Lu
- Nonparametric Image Registration Using Generalized Elastic Nets
- We have proposed the use of priors based on the Laplacian Eigenmaps Latent Variable Model (LELVM) for people tracking. LELVM is computationally efficient,
- In: Neural Computation 14(7):15451560 (Jul 2002) URL: http://cns.georgetown.edu/~miguel/papers/neco02.html
- Inverse problems and mapping 6.1 Introduction
- M&M: Multi-level Markov Model for Wireless Link Simulations Ankur Kamthe, Miguel A. Carreira-Perpi~nan and Alberto E. Cerpa
- A LATENT VARIABLE MODELLING APPROACH TO THE ACOUSTIC-TO-ARTICULATORY MAPPING PROBLEM
- A Computational Model for the Development of Multiple Maps in Primary Visual Cortex
- Generalised Blurring Mean-Shift Algorithms for Nonparametric Clustering Miguel A. Carreira-Perpi~nan
- In: IEEE Trans. on Pattern Analysis and Machine Intelligence 22(11): 1318-1323 (Nov. 2000) URL: http://www.dcs.shef.ac.uk/~miguel/papers/pami00.html
- 6 Conclusions .More general forms of cortical interaction can be intro
- ON DE LAS REDES DE NEURONAS DE COMPRESI '
- EUROPEAN SPACE AGENCY DIRECTORATE OF OPERATIONS
- Continuous latent variable models for dimensionality reduction
- People Tracking with the Laplacian Eigenmaps Latent Variable Model Zhengdong Lu Miguel A. Carreira-Perpi~nan
- Mode-finding for mixtures of Gaussian distributions Miguel A. Carreira-Perpi~nan
- The best method is ms1 spatial discreti-sation (possibly combined with ms4 EM
- Acceleration Strategies for Gaussian Mean-Shift Image Segmentation Miguel A. Carreira-Perpi~nan
- Experimental results We find that pDRUR is more likely than autoencoders and other methods to converge to a good optimum from a poor initial X. We conjecture that this is due to our effective optimization strategy and to the use of an enlarged search spac
- Parametric Dimensionality Reduction by Unsupervised Regression Miguel A. Carreira-Perpi~nan
- EUROPEAN SPACE AGENCY DIRECTORATE OF OPERATIONS
- Optimizing Visual Feature Perception for an Automatic Wearable Speech Supplement in Face-to-Face Communication and Classroom Situations
- KERNEL DENSITY ESTIMATION, AFFINITY-BASED CLUSTERING, AND TYPICAL CUTS Deniz Erdogmus Miguel A. Carreira-Perpi~nan Umut Ozertem
- TRAJECTORY INVERSE KINEMATICS BY NONLINEAR, NONGAUSSIAN TRACKING Chao Qin Miguel A. Carreira-Perpi~nan
- SEMI-SUPERVISED REGRESSION WITH TEMPORAL IMAGE SEQUENCES Ling Xie, Miguel A. Carreira-Perpi~nan and Shawn Newsam
- We have developed an old but ne-glected algorithm by providing a reli-
- Fast Nonparametric Clustering with Gaussian Blurring Mean-Shift Miguel A. Carreira-Perpi~nan MIGUEL@CSEE.OGI.EDU
- Differential Priors for Elastic Nets Miguel A. Carreira-Perpi~nan1
- OBSERVE: Occupancy-Based System for Efficient Reduction of HVAC Energy
- Non-parametric Image Registration Using Generalized Elastic Nets
- Dimension Reduction of Articulatory Data Miguel A. Carreira-Perpi~nana
- Conclusions and future work We have pointed out the importance of proximity graphs as scaffolds for clustering
- ENGINEERINGOGI NON-RIGID POINT SET REGISTRATION
- Gaussian mean shift is an EM algorithm Miguel A. Carreira-Perpi~nan
- Dimensionality reduction This chapter introduces and defines the problem of dimensionality reduction, discusses the topics of the curse
- Inverse problems and mapping 6.1 Introduction
- THE MODELLING OF THE THERMAL SUBSYSTEM IN SPACECRAFT REAL{TIME SIMULATORS
- 6 Conclusions More general forms of cortical interaction can be intro-
- In: Speech Communication 26(4), pp. 259-282 (December 1998) URL: http://www.dcs.shef.ac.uk/~miguel/papers/dim red epg.html
- Latent-variable representations for speech processing and research
- Latent-variable representations for speech processing and research
- A Review of Dimension Reduction Techniques Miguel A. Carreira-Perpi~nan
- In: Advances in Neural Information Processing Systems 12 (NIPS99), S.A. Solla, T.K. Leen & K.-R. Muller (eds.), 414-420, MIT Press (2000).
- The Laplacian Eigenmaps Latent Variable Model Miguel A. Carreira-Perpi~nan Zhengdong Lu
- School of Informatics, University of Edinburgh Institute for Adaptive and Neural Computation
- Gaussian mean shift is an EM algorithm A. CarreiraPerpinan
- THE MODELLING OF THE THERMAL SUBSYSTEM IN SPACECRAFT REAL--TIME SIMULATORS \Lambda
- Continuous latent variable models for dimensionality reduction
- Reconstruction of sequential data with probabilistic models and continuity constraints
- Future work Can apply same out-of-sample argument to LLE, etc.
- Latentvariable representations
- The Elastic Embedding Algorithm for Dimensionality Reduction Miguel A. Carreira-Perpi~nan mcarreira-perpinan@ucmerced.edu
- Continuous latent variable models for dimensionality reduction
- DENSITY GEODESICS FOR SIMILARITY CLUSTERING Umut Ozertem, Deniz Erdogmus
- In: Neural Computation 12(1), pp. 141-152 (January 2000) URL: http://www.dcs.shef.ac.uk/~miguel/papers/mix bernoulli.html
- Free-Form Nonrigid Image Registration Using Generalized Elastic Nets Andriy Myronenko, Xubo Song and Miguel A. Carreira-Perpi~nan
- In: Proc. of the 1999 IEE Colloquium on Applied Statistical Pattern Recognition, Birmingham, UK.
- iGlasses: An Automatic Wearable Speech Supplement in Face-to-Face Communication and Classroom Situations
- Conclusions We have introduced generalised versions of the GBMS algorithm for nonparametric clustering by
- A LATENT VARIABLE MODELLING APPROACH TO THE ACOUSTICTOARTICULATORY MAPPING PROBLEM
- In: Proc. of the 1999 IEE Colloquium on Applied Statistical Pattern Recognition, Birmingham, UK.
- In: Proc. of the 1998 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing
- In: Computational Neuroanatomy: Principles and Methods (G. A. Ascoli, ed.), Humana Press Inc., chapter 15, pp. 337-357, 2002
- Conclusions We explicitly represent multivalued mappings by exploiting the power of particle filters to represent multimodal distributions and using a mode-finding algorithm for Gaussian mixtures --
- Mode-nding for mixtures of Gaussian distributions A. Carreira-Perpi~n an
- In: Speech Communication 26(4), pp. 259282 (December 1998) URL: http://www.dcs.shef.ac.uk/~miguel/papers/dim red epg.html
- Proximity graphs for clustering and manifold A. CarreiraPerpi
- Conclusions and future work We introduce a machine learning method for trajectory IK that can deal with trajectories con-
- In: IEEE Trans. on Pattern Analysis and Machine Intelligence 22(11): 1318-1323 (Nov. 2000) URL: http://www.dcs.shef.ac.uk/~miguel/papers/pami00.html
- School of Informatics, University of Edinburgh Institute for Adaptive and Neural Computation
- Experiments with real-world data: the acoustic-to-articulatory mapping
- iGlasses: An Automatic Wearable Speech Supplement in Face-to-Face Communication and Classroom Situations
- APLICACION DE LAS REDES DE NEURONAS DE COMPRESION
- In: Proc. of the 1998 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing
- Wireless Link Simulations using Multi-level Markov Models Ankur U. Kamthe, Miguel . Carreira-Perpin and Alberto E. Cerpa
- Adaptation of a Mixture of Multivariate Bernoulli Distributions Ankur Kamthe and Miguel A. Carreira-Perpi~nan and Alberto E. Cerpa
- Our motivation is that nonlinear manifold learning algorithms can far outperform spectral methods
- Acceleration Strategies for Gaussian MeanShift Image Segmentation A. CarreiraPerpi n an
- Density Networks for Dimension Reduction of Continuous Data: Analytical Solutions \Lambda
- Reconstruction probabilistic
- People Tracking with the Laplacian Eigenmaps Latent Variable Model
- Clin Chem Lab Med 2007;45(6):749752 2007 by Walter de Gruyter Berlin New York. DOI 10.1515/CCLM.2007.177 2007/166 Article in press -uncorrected proof
- On Contrastive Divergence Learning Miguel A. Carreira-Perpi~nan
- 0 2 4 6 8 10 12 14 16 784 testseterror(%)
- Multiscale Conditional Random Fields for Image Labeling Xuming He Richard S. Zemel Miguel A. Carreira-Perpi~nan
- In: J. Neurophysiology 92(5):2947-2959 (Nov. 2004) URL: http://www.cse.ogi.edu/~miguel/papers.html
- In: Advances in Neural Information Processing Systems 12 (NIPS99), S.A. Solla, T.K. Leen & K.R. Muller (eds.), 414420, MIT Press (2000).
- Latentvariable representations
- Conclusions and future work We have shown that, in general, the fixed points of CD differ from those of ML, and thus CD is
- On the Number of Modes of a Gaussian Mixture Miguel A. Carreira-Perpi~nan1
- Reconstruction of sequential data with probabilistic models and continuity constraints
- Constrained Spectral Clustering through Affinity Propagation Zhengdong Lu
- Semi-supervised Image Segmentation Image Clustering Result First 10 Eigenvalues e2 e3 e4
- Fast Nonparametric Clustering with Gaussian Blurring MeanShift A. CarreiraPerpi
- In: Neural Computation 12(1), pp. 141152 (January 2000) URL: http://www.dcs.shef.ac.uk/~miguel/papers/mix bernoulli.html
- Experiments with realworld data: the acoustictoarticulatory mapping
- ENGINEERINGOGI FREE-FORM NON-RIGID IMAGE REGISTRATION
- People Tracking with the Laplacian Eigenmaps Latent Variable Model
- Reconstruction probabilistic
- The continuous latent variable modelling formalism
- RECONSTRUCTING THE FULL TONGUE CONTOUR FROM EMA/X-RAY MICROBEAM Chao Qin Miguel A. Carreira-Perpi~nan
- Continuous latent variable models for dimensionality reduction
- The Geometry of the Articulatory Region That Produces a Speech Sound Chao Qin and Miguel A. Carreira-Perpi~nan
- Dimensionality Reduction by Unsupervised Regression Miguel A. Carreira-Perpi~nan
- The continuous latent variable modelling formalism
- In: Neural Computation 14(7):1545-1560 (Jul 2002) URL: http://cns.georgetown.edu/~miguel/papers/neco02.html
- Proximity graphs for clustering and manifold Miguel A. Carreira-Perpi~nan Richard S. Zemel
- In: Computational Neuroanatomy: Principles and Methods (G. A. Ascoli, ed.), Humana Press Inc., chapter 15, pp. 337357, 2002
- Non-rigid point set registration: Coherent Point Drift Andriy Myronenko Xubo Song Miguel A. Carreira-Perpi~nan
- Trajectory Inverse Kinematics by Conditional Density Modes Chao Qin Miguel A. Carreira-Perpi~nan
- Machine learning models of the tongue shape during speech Miguel A. Carreira-Perpi~nan
- Adaptation of a mixture of multivariate Bernoulli distributions Ankur U. Kamthe, Miguel . Carreira-Perpin and Alberto E. Cerpa
- Introduction Prior research has shown that energy savings are
- Generalised elastic nets Miguel A. Carreira-Perpi~nan
- MACHINE LEARNING MODELS OF THE TONGUE SHAPE DURING SPEECH Miguel A. Carreira-Perpi~nan
- Reconstruction of sequential data with density models Miguel A. Carreira-Perpi~nan
- Manifold Learning and Missing Data Recovery through Unsupervised Regression Miguel A. Carreira-Perpi~nan
- Enabling Building Energy Auditing Using Adapted Occupancy Ankur Kamthe, Varick Erickson, Miguel A. Carreira-Perpi~nan and Alberto Cerpa
