no code implementations • 28 Feb 2022 • Nhat Thien Pham, Faicel Chamroukhi
We develop a mixtures-of-experts (ME) approach to the multiclass classification where the predictors are univariate functions.
1 code implementation • 31 Jan 2022 • Segolene Brivet, Faicel Chamroukhi, Mark Coates, Reza Forghani, Peter Savadjiev
In this paper, we develop novel functional data analysis (FDA) techniques and adapt them to the analysis of DECT decay curves.
no code implementations • 18 Apr 2021 • TrungTin Nguyen, Faicel Chamroukhi, Hien Duy Nguyen, Florence Forbes
This model selection criterion allows us to handle the challenging problem of inferring the number of mixture components, the degree of polynomial mean functions, and the hidden block-diagonal structures of the covariance matrices, which reduces the number of parameters to be estimated and leads to a trade-off between complexity and sparsity in the model.
1 code implementation • 6 Apr 2021 • TrungTin Nguyen, Hien Duy Nguyen, Faicel Chamroukhi, Florence Forbes
Mixture of experts (MoE) are a popular class of statistical and machine learning models that have gained attention over the years due to their flexibility and efficiency.
no code implementations • 22 Sep 2020 • TrungTin Nguyen, Hien D. Nguyen, Faicel Chamroukhi, Geoffrey J. McLachlan
Mixture of experts (MoE) has a well-principled finite mixture model construction for prediction, allowing the gating network (mixture weights) to learn from the predictors (explanatory variables) together with the experts' network (mixture component densities).
1 code implementation • 14 Jul 2019 • Bao Tuyen Huynh, Faicel Chamroukhi
Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for clustering.
no code implementations • 29 Oct 2018 • Faicel Chamroukhi, Bao-Tuyen Huynh
Mixture of Experts (MoE) are successful models for modeling heterogeneous data in many statistical learning problems including regression, clustering and classification.
no code implementations • 1 Mar 2018 • Faicel Chamroukhi, Hien D. Nguyen
FDA is the data analysis paradigm in which the individual data units are functions (e. g., curves, surfaces), rather than simple vectors.
no code implementations • 12 Jul 2017 • Hien D. Nguyen, Faicel Chamroukhi
Due to the probabilistic nature of MoE models, we propose the maximum quasi-likelihood (MQL) estimator as a method for estimating MoE model parameters from data, and we provide conditions under which MQL estimators are consistent and asymptotically normal.
no code implementations • 9 Dec 2016 • Faicel Chamroukhi
Mixture of Experts (MoE) is a popular framework in the fields of statistics and machine learning for modeling heterogeneity in data for regression, classification and clustering.
no code implementations • 9 Dec 2016 • Faicel Chamroukhi
For regression and cluster analyses of continuous data, MoE usually use normal experts following the Gaussian distribution.
no code implementations • 4 Aug 2015 • Faicel Chamroukhi
Then, in order to model populations of spatial functional data issued from heterogeneous groups, we integrate the BSSR model into a mixture framework.
3 code implementations • 22 Jun 2015 • Faicel Chamroukhi
Mixture of Experts (MoE) is a popular framework for modeling heterogeneity in data for regression, classification and clustering.
no code implementations • 14 Jan 2015 • Faicel Chamroukhi, Marius Bartcus, Hervé Glotin
The proposed DPPM models are Bayesian nonparametric parsimonious mixture models that allow to simultaneously infer the model parameters, the optimal number of mixture components and the optimal parsimonious mixture structure from the data.
no code implementations • 24 Sep 2014 • Faicel Chamroukhi
The proposed learning approach is fully unsupervised: 1) it simultaneously infers the model parameters and the optimal number of the regression mixture components from the data as the learning proceeds, rather than in a two-fold scheme as in standard model-based clustering using afterward model selection criteria, and 2) it does not require accurate initialization unlike the standard EM for regression mixtures.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
A new approach for signal parametrization, which consists of a specific regression model incorporating a discrete hidden logistic process, is proposed.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
The parameters of the hidden logistic process, in the inner loop of the EM algorithm, are estimated using a multi-class Iterative Reweighted Least-Squares (IRLS) algorithm.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi
Our approach both handles the problem of initialization and the one of choosing the optimal number of clusters as the EM learning proceeds, rather than in a two-fold scheme.
no code implementations • 25 Dec 2013 • Raïssa Onanena, Faicel Chamroukhi, Latifa Oukhellou, Denis Candusso, Patrice Aknin, Daniel Hissel
This paper describes a pattern recognition approach aiming to estimate fuel cell duration time from electrochemical impedance spectroscopy measurements.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Hervé Glotin
More specifically, we propose a new mixture model-based discriminant analysis approach for functional data using a specific hidden process regression model.
no code implementations • 25 Dec 2013 • Allou Samé, Faicel Chamroukhi, Gérard Govaert, Patrice Aknin
The proposed approach can also be regarded as a clustering approach which operates by finding groups of time series having common changes in regime.
no code implementations • 25 Dec 2013 • Dorra Trabelsi, Samer Mohammed, Faicel Chamroukhi, Latifa Oukhellou, Yacine Amirat
This paper presents a new unsupervised approach for human activity recognition from raw acceleration data measured using inertial wearable sensors.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Samer Mohammed, Dorra Trabelsi, Latifa Oukhellou, Yacine Amirat
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
A new approach for functional data description is proposed in this paper.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
This paper proposes a method of segmenting temporal data into ordered classes.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
A new approach for time series modeling is proposed in this paper.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Hervé Glotin, Allou Samé
We propose a new model-based functional mixture discriminant analysis approach based on a specific hidden process regression model that governs the regime changes over time.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Patrice Aknin, Gérard Govaert
Comparisons with existing approaches for time series clustering, including the stand EM for Gaussian mixtures, $K$-means clustering, the standard mixture of regression models and mixture of Hidden Markov Models, demonstrate the effectiveness of the proposed approach.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Heré Glotin, Céline Rabouy
We present a new mixture model-based discriminant analysis approach for functional data using a specific hidden process regression model.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi
The proposed approach is evaluated using simulated curves and real-world curves.
no code implementations • 25 Dec 2013 • Faicel Chamroukhi, Allou Samé, Gérard Govaert, Patrice Aknin
A non linear regression approach which consists of a specific regression model incorporating a latent process, allowing various polynomial regression models to be activated preferentially and smoothly, is introduced in this paper.