Staged Mixture Modelling and Boosting
نویسندگان
چکیده
In this paper, we introduce and evaluate a data-driven staged mixture modeling tech nique for building density, regression, and classification models. Our basic approach is to sequentially add components to a finite mixture model using the structural expec tation maximization (SEM) algorithm. We show that our technique is qualitatively sim ilar to boosting. This correspondence is a natural byproduct of the fact that we use the SEM algorithm to sequentially fit the mixture model. Finally, in our experimental evaluation, we demonstrate the effectiveness of our approach on a variety of prediction and density estimation tasks using real-world data.
منابع مشابه
Staged Mixture Modeling and Boosting
In this paper, we introduce and evaluate a data-driven staged mixture modeling technique for building density, regression, and classi cation models. Our basic approach is to sequentially add components to a nite mixture model using the structural expectation maximization (SEM) algorithm. We show that our technique is qualitatively similar to boosting. This correspondence is a natural byproduct ...
متن کاملSPORE: Staged Probabilistic Regression for Hand Orientation Inference
Learning the global hand orientation from 2D monocular images is a challenging task, as the projected hand shape is affected by a number of variations. These include inter-person hand shape and size variations, intra-person pose and style variations and self-occlusion due to varying hand orientation. Given a hand orientation dataset containing these variations, a single regressor proves to be l...
متن کاملSkew Laplace Finite Mixture Modelling
‎This paper presents a new mixture model via considering the univariate skew Laplace distribution‎. ‎The new model can handle both heavy tails and skewness and is multimodal‎. ‎Describing some properties of the proposed model‎, ‎we present a feasible EM algorithm for iteratively‎ ‎computing maximum likelihood estimates‎. ‎We also derive the observ...
متن کاملBoosting GMM and Its Two Applications
Boosting is an effecient method to improve the classification performance. Recent theoretical work has shown that the boosting technique can be viewed as a gradient descent search for a good fit in function space. Several authors have applied such viewpoint to solve the density estimation problems. In this paper we generalize such framework to a specific density model – Gaussian Mixture Model (...
متن کامل