Results 1  10
of
13
Combining Multiple Representations and Classifiers for Handwritten Digit Recognition
 Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
, 1997
"... We investigate techniques to combine multiple representations of a handwritten digit to increase classification accuracy without significantly increasing system complexity or recognition time. We compare multiexpert and multistage combination techniques and discuss in detail in a comparative manner ..."
Abstract

Cited by 22 (2 self)
 Add to MetaCart
We investigate techniques to combine multiple representations of a handwritten digit to increase classification accuracy without significantly increasing system complexity or recognition time. We compare multiexpert and multistage combination techniques and discuss in detail in a comparative manner methods for combining multiple learners: Voting, mixture of experts, stacking, boosting and cascading. In penbased handwritten character recognition, the input is the dynamic movement of the pentip over the pressure sensitive tablet. There is also the image formed as a result of this movement. On a realworld database, we notice that the two multilayer perceptron (MLP) neural networkbased classifiers using separately these representations make errors on different patterns implying that a suitable combination of the two would lead to higher accuracy. Thus we implement and compare voting, mixture of experts, stacking and cascading. Combined classifiers have an error percentage less than ind...
Techniques for Combining Multiple Learners
 Proceedings of Engineering of Intelligent Systems
, 1998
"... Learners based on different paradigms can be combined for improved accuracy. Each learning method assumes a certain model that comes with a set of assumptions which may lead to error if the assumptions do not hold. Learning is an illposed problem and with finite data each algorithm converges to a d ..."
Abstract

Cited by 18 (0 self)
 Add to MetaCart
(Show Context)
Learners based on different paradigms can be combined for improved accuracy. Each learning method assumes a certain model that comes with a set of assumptions which may lead to error if the assumptions do not hold. Learning is an illposed problem and with finite data each algorithm converges to a different solution and fails under different circumstances. Our previous experience with statistical and neural classifiers was that classifiers based on these paradigms do generalize differently, fail on different patterns and to a certain extent complement each other and thus we look for ways to combine them for higher accuracy. One way to get complementary classifiers is by using different input representations. The methods we investigate are voting, mixture of experts, stacking and cascading. We do experiments on three realworld applications: optical handwritten digit recognition, penbased handwritten digit recognition and the estimation of road travel distances which is a regression pr...
Class Visualization of HighDimensional Data with Applications
, 2003
"... Consider the problem of visualizing highdimensional data that has been categorized into various classes. Our goal in visualizing is to quickly absorb interclass and intraclass relationships. Towards this end, classpreserving projections of the multidimensional data onto twodimensional planes, ..."
Abstract

Cited by 17 (0 self)
 Add to MetaCart
(Show Context)
Consider the problem of visualizing highdimensional data that has been categorized into various classes. Our goal in visualizing is to quickly absorb interclass and intraclass relationships. Towards this end, classpreserving projections of the multidimensional data onto twodimensional planes, which can be displayed on a computer screen, are introduced. These classpreserving projections maintain the highdimensional class structure, and are closely related to Fisher's linear discriminants. By displaying sequences of such twodimensional projections and by moving continuously from one projection to the next, an illusion of smooth motion through a multidimensional display can be created. We call such sequences class tours. Furthermore, we overlay classsimilarity graphs on our twodimensional projections to capture the distance relationships in the original highdimensional space. We illustrate
Refined Shared Nearest Neighbors Graph for Combining Multiple Data Clusterings
"... Abstract. We recently introduced the idea of solving cluster ensembles using a Weighted Shared nearest neighbors Graph (WSnnG). Preliminary experiments have shown promising results in terms of integrating different clusterings into a combined one, such that the natural cluster structure of the data ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
(Show Context)
Abstract. We recently introduced the idea of solving cluster ensembles using a Weighted Shared nearest neighbors Graph (WSnnG). Preliminary experiments have shown promising results in terms of integrating different clusterings into a combined one, such that the natural cluster structure of the data can be revealed. In this paper, we further study and extend the basic WSnnG. First, we introduce the use of fixed number of nearest neighbors in order to reduce the size of the graph. Second, we use refined weights on the edges and vertices of the graph. Experiments show that it is possible to capture the similarity relationships between the data patterns on a compact refined graph. Furthermore, the quality of the combined clustering based on the proposed WSnnG surpasses the average quality of the ensemble and that of an alternative clustering combining method based on partitioning of the patterns ’ coassociation matrix. 1
Discernibility Concept in Classification Problems
"... The main idea behind this project is that the pattern classification process can be enhanced by taking into account the geometry of class structure in datasets of interest. In contrast to previous work in the literature, this research not only develops a measure of discernibility of individual patte ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
The main idea behind this project is that the pattern classification process can be enhanced by taking into account the geometry of class structure in datasets of interest. In contrast to previous work in the literature, this research not only develops a measure of discernibility of individual patterns but also consistently applies it to various stages of the classification process. The applications of the discernibility concept cover a wide range of issues from preprocessing to the actual classification and beyond that. Specifically, we apply it for: (a) finding feature subsets of similar classification quality (applicable in diverse ensembles), (b) feature selection, (c) data reduction, (d) reject option, and (e) enhancing the kNN classifier. Also, a number of auxiliary algorithms and measures are developed to facilitate the proposed methodology. Experiments have been carried out using datasets of the University of California at Irvine (UCI) repository. The experiments provide numerical evidence that the proposed approach does improve the performance of various classifiers. This, together with its simplicity renders it a novel,
Semilazy learning: combining clustering and classifiers to build more accurate models
 In Proceedings of the 2003 International Conference on Machine Learning; Models, Technologies and Applications (MLMTA
, 2003
"... Eager learners such as neural networks, decision trees, and naïve Bayes classifiers construct a single model from the training data before observing any test set instances. In contrast, lazy learners such as Knearest neighbor consider a test set instance before they generalize beyond the training d ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Eager learners such as neural networks, decision trees, and naïve Bayes classifiers construct a single model from the training data before observing any test set instances. In contrast, lazy learners such as Knearest neighbor consider a test set instance before they generalize beyond the training data. This allows making predictions from only a specific selection of instances most similar to the test set instance which has been shown to outperform eager learners on a number of problems. However, lazy learners require the storing and querying of the entire training data set for each instance which is unsuitable for the large amounts of data typically found in many applications. We introduce and illustrate the benefits of an example of semilazy learning that combines clustering and classification models and has the benefits of eager and lazy learners. We propose dividing the instances using clusterbased segmentation and then using an eager learner to build a classification model for each cluster. This has the effect of dividing the instance space into a number of distinct regions and building a local model for each. Our experiments on UCI data sets show clustering the data into segments then building classification models using a variety of eager learners for each segment often results in a greater overall crossvalidated accuracy than building a single model or using a pure lazy approach such as KNearestNeighbor. We can also consider our approach to semilazy learning as an example of the divide and conquer (DAC) strategy used in many scientific fields to divide a complex problem into a set of simpler problems. Finally, we find that the misclassified instances are more likely to be outliers with respect to the clustering segmentation. 1
Appears in Pattern Recognition (accepted August 2009) Parsimonious reduction of Gaussian mixture models with a variationalBayes approach ∗
, 2009
"... Aggregating statistical representations of classes is an important task for current trends in scaling up learning and recognition, or for addressing them in distributed infrastructures. In this perspective, we address the problem of merging probabilistic Gaussian mixture models in an efficient way, ..."
Abstract
 Add to MetaCart
(Show Context)
Aggregating statistical representations of classes is an important task for current trends in scaling up learning and recognition, or for addressing them in distributed infrastructures. In this perspective, we address the problem of merging probabilistic Gaussian mixture models in an efficient way, through the search for a suitable combination of components from mixtures to be merged. We propose a new Bayesian modelling of this combination problem, in association to a variational estimation technique, that handles efficiently the model complexity issue. A main feature of the present scheme is that it merely resorts to the parameters of the original mixture, ensuring low computational cost and possibly communication, should we operate on a distributed system. Experimental results are reported on real data. This work was funded by ANR Safimage, in particular through P. Bruneau’s Ph.D. grant
Dynamic Alignment Distance Based Online Signature Verification
"... Abstract. A selfcontained application that verifies the signatures of enrolled users is developed. The verifier uses dissimilarity values based on dynamic alignment distances. Three different threshold calculation techniques are investigated: The first one makes use of the information provided by f ..."
Abstract
 Add to MetaCart
Abstract. A selfcontained application that verifies the signatures of enrolled users is developed. The verifier uses dissimilarity values based on dynamic alignment distances. Three different threshold calculation techniques are investigated: The first one makes use of the information provided by forged signatures and the other two methods use the information gathered from genuine signatures. The methods are evaluated on two different datasets: One with skilled forgery and the other with random forgery. Best results are obtained by using both genuine and forgery information to calculate the threshold. The lowest reported total error value for the dataset with skilled forgeries is 7.83 percent. 1
Support Vector Machines of Intervalbased
"... In previous works, a time series classification system has been presented. It is based on boosting very simple classifiers, formed only by one literal. The used literals are based on temporal intervals. ..."
Abstract
 Add to MetaCart
In previous works, a time series classification system has been presented. It is based on boosting very simple classifiers, formed only by one literal. The used literals are based on temporal intervals.
Support Vector Machines of
"... In previous works, a time series classification system has been presented. ..."
Abstract
 Add to MetaCart
In previous works, a time series classification system has been presented.