A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Selection and Discriminative Estimation of Orthogonal Gaussian Mixture Models for Handwritten Digit Recognition
2009
2009 10th International Conference on Document Analysis and Recognition
Preserved Fulltext
We apply the proposed learning approach of OGMM to handwritten digit recognition. ...
After the model selection is completed, a discriminative learning framework of Bayesian classifiers called Max-Min posterior pseudoprobabilities (MMP) is employed to estimate component parameters in OGMM ...
Acknowledges The authors would like to thank Dr. Cheng-Lin Liu for providing the e-grg features of handwritten digits. ...
doi:10.1109/icdar.2009.44
dblp:conf/icdar/ChenLJ09
fatcat:oxwbehbnmvfhfc5qxw3ppv5boa
Statistical Modeling and Learning for Recognition-Based Handwritten Numeral String Segmentation
2009
2009 10th International Conference on Document Analysis and Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Based on this modeling, the recognition based segmentation is solved under the Max-Min posterior Pseudo-probabilities (MMP) framework of learning Bayesian classifiers. ...
In the training phase, we use the MMP method to learn a posterior pseudo-probability measure function from positive samples and negative samples of numeral strings segmented correctly. ...
Unknown parameters in the posterior pseudo-probability measure function are learned from the training data by the MMP method. ...
doi:10.1109/icdar.2009.25
dblp:conf/icdar/WangLJ09
fatcat:ffy2hpyn2nhaxnyyoqmudipn2a
Discriminative structure selection method of Gaussian Mixture Models with its application to handwritten digit recognition
2011
Neurocomputing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
We introduce a GMM structure selection criterion based on a discriminative objective function called Soft target based Max-Min posterior Pseudo-probabilities (Soft-MMP). ...
We evaluate the proposed GMM structure selection method through the experiments of handwritten digit recognition on the well-known CENPARMI and MNIST digit databases. ...
The used discriminative learning criterion is SOFT target based Max-Min posterior Pseudo-probabilities (Soft-MMP) [20] . ...
doi:10.1016/j.neucom.2010.11.010
fatcat:j67jprdt3vgvfj7sevb6qkvtp4
Combining evolution strategy and gradient descent method for discriminative learning of bayesian classifiers
2009
Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2012; you can also visit the original URL.
The file type is application/pdf.
posterior Pseudo-probabilities (Soft-MMP) learning framework. ...
As a result, the efficiency and the effectiveness of the CMA-ES are improved. We apply the Soft-MMP with the proposed hybrid optimization approach to handwritten digit recognition. ...
ACKNOWLEDGEMENTS The authors would like to thank Dr. Cheng-Lin Liu for providing the e-grg features of handwritten digits and the referees for their valuable comments and suggestions. This ...
doi:10.1145/1569901.1569972
dblp:conf/gecco/ChenLJ09
fatcat:sbyfev76qvbufiqj4ajykcvxxi
Objective Function Design for MCE-Based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japanese Text Recognition
2011
2011 International Conference on Document Analysis and Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper describes effective object function design for combining on-line and off-line character recognizers for on-line handwritten Japanese text recognition. ...
Moreover, we apply a genetic algorithm to estimate super parameters such as the number of clusters, initial learning rate and maximum learning times as well as the sigmoid function parameter for MCE optimization ...
same parameters, secondly, we apply α, ω, ε, T to learn the weighting parameters by MCE to obtain a smallest MCE criterion L min MCE , and set 1-L min MCE as the fitness of each chromosome {G, α, ω, ε, ...
doi:10.1109/icdar.2011.125
dblp:conf/icdar/ZhuGN11
fatcat:ouqjit3ucvfkniotvfo4vxoo5e
Active graph based semi-supervised learning using image matching: Application to handwritten digit recognition
2016
Pattern Recognition Letters
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
The robustness of the method is highlighted by the performance of handwritten digit recognition in different scripts. ...
In this paper, we present a novel active learning strategy for the classification of handwritten digits. ...
Acknowledgment The author would like to thank Prof. Ujjwal Bhattacharya for sharing the databases of Bangla, Devnagari, and Oriya. ...
doi:10.1016/j.patrec.2016.01.016
fatcat:dijkntjghbhd3erzofruiv6oni
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The experiments are conducted on two weakly-supervised neural-symbolic tasks: (1) handwritten formula recognition on the newly introduced HWF dataset; (2) visual question answering on the CLEVR dataset ...
Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the symbolic reasoning module and thus converge slowly with sparse rewards ...
We thank Baoxiong Jia for helpful discussion on the generalized Earley Parser. This work reported herein is supported by ARO W911NF1810296, DARPA XAI N66001-17-2-4029, and ONR MURI N00014-16-1-2007. ...
arXiv:2006.06649v2
fatcat:nbr5yyhaqzbkjfdb7z2om2db34
Generative OpenMax for Multi-Class Open Set Classification
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We validate the proposed method on two datasets of handwritten digits and characters, resulting in superior results over previous deep learning based method OpenMax Moreover, G-OpenMax provides a way to ...
The proposed method, called Gener- ative OpenMax (G-OpenMax), extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis. ...
Those methods model the known class distribution using a parametric model from which the posterior probabilities of a test sample are computed. ...
arXiv:1707.07418v1
fatcat:hdd6satvqne77glzyqgdebcr4e
COMBINING MODEL-BASED AND DISCRIMINATIVE APPROACHES IN A MODULAR TWO-STAGE CLASSIFICATION SYSTEM: APPLICATION TO ISOLATED HANDWRITTEN DIGIT RECOGNITION
[chapter]
2009
Series in Machine Perception and Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
In the first stage we estimate the posterior probabilities with a model-based approach and we re-estimate only the highest probabilities with appropriate Support Vector Classifiers (SVC) in the second ...
Finally, the first experiments on the benchmark database MNIST have shown that our dynamic classification process allows to maintain the accuracy of SVCs, while decreasing complexity by a factor 8.7 and ...
Experimental results To evaluate our method, we chose a classical pattern recognition problem: isolated handwritten digit recognition. ...
doi:10.1142/9789812834461_0011
dblp:series/smpai/MilgramSC09
fatcat:xn5xwtia7fhd3lwcd237zykgn4
Combining Model-based and Discriminative Approaches in a Modular Two-stage Classification System: Application to Isolated Handwritten Digit Recognition
2005
ELCVIA Electronic Letters on Computer Vision and Image Analysis
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
In the first stage we estimate the posterior probabilities with a model-based approach and we re-estimate only the highest probabilities with appropriate Support Vector Classifiers (SVC) in the second ...
Finally, the first experiments on the benchmark database MNIST have shown that our dynamic classification process allows to maintain the accuracy of SVCs, while decreasing complexity by a factor 8.7 and ...
Experimental results To evaluate our method, we chose a classical pattern recognition problem: isolated handwritten digit recognition. ...
doi:10.5565/rev/elcvia.92
fatcat:nganv5b33zdsljnx7nyxdpcqkq
Convex Optimizations for Distance Metric Learning and Pattern Classification [Applications Corner
2010
IEEE Signal Processing Magazine
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
EXPERIMENTAL RESULTS We experimented with LMNN classification on problems in face recognition and handwritten digit recognition. ...
For digit recognition, we experimented with images from an extensively benchmarked data set of handwritten digits (available at http://yann.lecun.com/ exdb/mnist). ...
[SP] define a valid distance metric; second, because linear inequalities in the elements of this matrix can ensure that inputs are correctly labeled by kNN classification or Gaussian mixture modeling. ...
doi:10.1109/msp.2010.936013
fatcat:ffx2slovabbelmoil7nz2iptia
Online EM for Functional Data
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our sequential inference framework is significantly more computationally efficient than equivalent batch learning algorithms, especially when the missing data is high-dimensional. ...
A novel approach to perform unsupervised sequential learning for functional data is proposed. ...
Acknowledgments This work has been supported by the ONERA, the French Aerospace Lab and the DGA, the French Procurement Agency. ...
arXiv:1604.00570v1
fatcat:44kzhojuwralnodhvivhxzdoju
Optimally combining a cascade of classifiers
2006
Document Recognition and Retrieval XIII
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The effectiveness of the approach is demonstrated on handwritten character recognition by finding a) the fastest possible combination given an upper bound on classification error, and also b) the most ...
The search procedure only updates the rejection thresholds (one for each constituent classier) in the cascade, consequently no new classifiers are added and no training is necessary. ...
One such network achieved the best known error rate of 0.4% [7] for handwritten digit recognition on (MNIST). ...
doi:10.1117/12.643669
dblp:conf/drr/ChellapillaSS06
fatcat:jjswwl7py5az7pa5jboamhkqpq
Online EM for functional data
2017
Computational Statistics & Data Analysis
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The designed sequential inference framework is significantly more computationally efficient than equivalent batch learning algorithms, especially when the missing data is high-dimensional. ...
A novel approach to perform unsupervised sequential learning for functional data is proposed. ...
Florian Maire would like to thank the ONERA-The French Aerospace Lab and the DGA-The French Procurement Agency. ...
doi:10.1016/j.csda.2017.01.006
fatcat:iwf4xqxjknb6nnjo6gby3ysqui
A multi-class structured dictionary learning method using discriminant atom selection
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Our method was tested with a widely used database for handwritten digit recognition and compared with three state-of-the-art classification methods. ...
The results show that our method significantly outperforms the other three achieving good recognition rates and additionally, reducing the computational cost of the classifier. ...
The method was tested with a widely used database for handwritten digit recognition and compared with three state-of-the-art classification methods. ...
arXiv:1812.01389v1
fatcat:ulsl5l6qnnazplypw4jld3ltne
« Previous
Showing results 1 — 15 out of 253 results