Filters








390 Hits in 4.8 sec

A Comparative Evaluation of Curriculum Learning with Filtering and Boosting [article]

Michael R. Smith, Tony Martinez
2013 arXiv   pre-print
In this paper, we present an automated method that orders the instances in a data set by complexity based on the their likelihood of being misclassified (instance hardness).  ...  Not all instances in a data set are equally beneficial for inferring a model of the data. Some instances (such as outliers) are detrimental to inferring a model of the data.  ...  By filtering the noisy and outlier instances prior to training, AdaBoost does not overfit the noise since it is no longer in the training data.  ... 
arXiv:1312.4986v1 fatcat:6fjfvcj26nghnibrajk7knrx2i

Action retrieval with relevance feedback on YouTube videos

Simon Jones, Ling Shao
2011 Proceedings of the Third International Conference on Internet Multimedia Computing and Service - ICIMCS '11  
Among other techniques, we explore soft-assignment codebook clustering, feature pruning, motion and static features, Adaboost and ABRS-SVM for relevance feedback.  ...  In this paper, we investigate applying content-based retrieval with relevance feedback to the popular YouTube human action dataset[8], using a variety of methods to extract and compare features, in order  ...  Feature type Cluster assign RF 1 Static Hard Naive 2 Motion Hard Naive 3 Hybrid Hard Naive 4 Hybrid Soft Naive 5 Hybrid Hard Adaboost 6 Hybrid Hard ABRS-SVM  ... 
doi:10.1145/2043674.2043687 dblp:conf/icimcs/JonesS11 fatcat:migvpjz545buzofsuvccnnuwmi

Attention Tree: Learning Hierarchies of Visual Features for Large-Scale Image Recognition [article]

Priyadarshini Panda, Kaushik Roy
2016 arXiv   pre-print
In this paper, we present a tree-based classifier: Attention Tree (ATree) for large-scale image classification that uses recursive Adaboost training to construct a visual attention hierarchy.  ...  The proposed framework has been evaluated on both Caltech-256 and SUN datasets and achieves accuracy improvement over state-of-the-art tree-based methods at significantly lower computational cost.  ...  Fig. 1 ( 1 right) shows a toy example of an ATree based Fig. 1 . 1 Fig. 1.  ... 
arXiv:1608.00611v1 fatcat:6h46ni5berajxmslj4dixmymbm

Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering

Zhuowen Tu
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
Also, clustering is naturally embedded in the learning phase and each sub-tree represents a cluster of certain level.  ...  The top node of the tree therefore outputs the overall posterior probability by integrating the probabilities gathered from its sub-trees.  ...  Acknowledgment I thank Xiang (Sean) Zhou, Xiangrong Chen, Tao Zhao, Adrian Barbu, Piotr Dollar, and Xiaodong Fan for helpful comments and assistance in getting some of the training datasets.  ... 
doi:10.1109/iccv.2005.194 dblp:conf/iccv/Tu05a fatcat:7qy4k7vuerexzbc5avoq4ohz7a

Data Mining, Machine Learning and Big Data Analytics

Lidong Wang
2017 International Transaction of Electrical and Computer Engineers System  
The feasibility and challenges of the applications of deep learning and traditional data mining and machine learning methods in Big Data analytics are also analyzed and presented.  ...  This paper analyses deep learning and traditional data mining and machine learning methods; compares the advantages and disadvantage of the traditional methods; introduces enterprise needs, systems and  ...  Taking clustering as an example, a natural way of clustering big data is to extend existing methods (such as k-means) so that they can cope with the huge workloads.  ... 
doi:10.12691/iteces-4-2-2 fatcat:bk3lvlmikjdqhfejqrrxjdq5eq

Pruned Random Subspace Method for One-Class Classifiers [chapter]

Veronika Cheplygina, David M. J. Tax
2011 Lecture Notes in Computer Science  
In this paper we show that the performance by the RSM can be noisy, and that pruning inaccurate classifiers from the ensemble can be more effective than using all available classifiers.  ...  We propose to apply pruning to RSM of one-class classifiers using a supervised AUC criterion or an unsupervised consistency criterion.  ...  Surprisingly, also AdaBoost did not perform very well. AdaBoost is originally developed to boost two-class classifiers by reweighing training objects.  ... 
doi:10.1007/978-3-642-21557-5_12 fatcat:sh7nqkruibf6nega2dxlxn2jky

Data-driven exemplar model selection

Ishan Misra, Abhinav Shrivastava, Martial Hebert
2014 IEEE Winter Conference on Applications of Computer Vision  
The current approaches do this by using mixtures of models, where each mixture is designed to capture one (or a few) axis of variation.  ...  Another issue is the requirement of a large set of training images to capture such variations.  ...  Acknowledgement: This work was supported in part by NSF Grant IIS1065336 and a Siebel Scholarship. The authors wish to thank Francisco Vicente and Ricardo Cabral for helpful discussions.  ... 
doi:10.1109/wacv.2014.6836080 dblp:conf/wacv/MisraSH14 fatcat:io35rfhlh5bx3pky57rxkjbqhi

An Analysis of Ensemble Pruning Techniques Based on Ordered Aggregation

G. Martinez-Muoz, D. Hernandez-Lobato, A. Suarez
2009 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This minimum lies below the asymptotic error of bagging. Pruned ensembles are obtained by retaining a fraction of the classifiers in the ordered ensemble.  ...  The pruning methods investigated are based on modifying the order of aggregation of classifiers in the ensemble. In the original bagging algorithm, the order of aggregation is left unspecified.  ...  A different method for ensemble pruning is to replace the ensemble by a set of classifiers using clustering.  ... 
doi:10.1109/tpami.2008.78 pmid:19110491 fatcat:jzpohrqz5veq3ocolk7ti4grqy

Top 10 algorithms in data mining

Xindong Wu, Vipin Kumar, J. Ross Quinlan, Joydeep Ghosh, Qiang Yang, Hiroshi Motoda, Geoffrey J. McLachlan, Angus Ng, Bing Liu, Philip S. Yu, Zhi-Hua Zhou, Michael Steinbach (+2 others)
2007 Knowledge and Information Systems  
This paper presents the top 10 data mining algorithms identified by the IEEE International Conference on Data Mining (ICDM) in December 2006: C4.5, k-Means, SVM, Apriori, EM, PageRank, AdaBoost, kNN, Naive  ...  All remaining (18) nominations were then organized in 10 topics: association analysis, classification, clustering, statistical learning, bagging and boosting, sequential patterns, integrated mining, rough  ...  The initial tree is then pruned to avoid overfitting.  ... 
doi:10.1007/s10115-007-0114-2 fatcat:zire76whxjdtzjmncv2nlvztme

Ensemble approaches for regression

João Mendes-Moreira, Carlos Soares, Alípio Mário Jorge, Jorge Freire De Sousa
2012 ACM Computing Surveys  
The process of ensemble learning can be divided into three phases: the generation phase, the pruning phase, and the integration phase.  ...  We discuss different approaches to each of these phases that are able to deal with the regression problem, categorizing them in terms of their relevant characteristics and linking them to contributions  ...  VI Summary on Methods for Ensemble Pruning Using Partitioning-Based Approaches Name Stopping criterion Evaluation measure Clustering by Partitioning: given number of clusters Partitioning: weighted distance  ... 
doi:10.1145/2379776.2379786 fatcat:7mfwduuedrcmzlwjr6sic2vyei

BioTextRetriever

Célia Talma Gonçalves, Rui Camacho, Eugénio Oliveira
2011 International Journal of Knowledge Discovery in Bioinformatics  
Finally we use that classifier to automatically enlarge the set of relevant papers by searching the MEDLINE using the automatically constructed classifier.  ...  In current web sites and data bases of sequences there are, usually, a set of curated paper references linked to each sequence.  ...  We have applied a collection of base learners and also ensemble learners.  ... 
doi:10.4018/jkdb.2011070102 fatcat:2m6zqivc75au3li6blrjwhivym

Novel Based Ensemble Machine Learning Classifiers for Detecting Breast Cancer

Taarun Srinivas, Aditya Krishna Karigiri Madhusudhan, Joshuva Arockia Dhanraj, Rajasekaran Chandra Sekaran, Neda Mostafaeipour, Negar Mostafaeipour, Ali Mostafaeipour, Ramin Ranjbarzadeh
2022 Mathematical Problems in Engineering  
The performance of the ensemble model in both platforms is compared based on metrics like accuracy, precision, recall, and sensitivity and investigated in detail.  ...  Of all the innovations in the field of ML models, the most significant ones have turned out to be in medicine and healthcare, since it has assisted doctors in the treatment of different types of diseases  ...  Pruning reduces the size of decision trees by removing nodes of the tree that do not contribute to model training.  ... 
doi:10.1155/2022/9619102 fatcat:ynuu35h2yjeyvntt364y57jbvm

Generating Diverse Ensembles to Counter the Problem of Class Imbalance [chapter]

T. Ryan Hoens, Nitesh V. Chawla
2010 Lecture Notes in Computer Science  
One of the more challenging problems faced by the data mining community is that of imbalanced datasets.  ...  We conclude by analyzing the performance of the ensembles, and showing that, overall, our technique provides a significant improvement.  ...  Acknowledgements Work was supported in part by the NSF Grant ECCS-0926170 and the Notebaert Premier Fellowship.  ... 
doi:10.1007/978-3-642-13672-6_46 fatcat:vc5o5f6bend6pauz7yxjuoiwwy

Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey [article]

Görkem Algan, Ilkay Ulusoy
2021 arXiv   pre-print
This paper aims to present these algorithms while categorizing them into one of the two subgroups: noise model based and noise model free methods.  ...  Although deep neural networks are known to be relatively robust to label noise, their tendency to overfit data makes them vulnerable to memorizing even random noise.  ...  Therefore, noise-robust alternatives of AdaBoost is proposed in literature, such as noise detection based AdaBoost [133] , rBoost [134] , RBoost1&RBoost2 [135] and robust multi-class AdaBoost [136  ... 
arXiv:1912.05170v3 fatcat:k5zm5k5e5bevph2abvwxkwr7qm

Empirical Performance Analysis of Decision Tree and Support Vector Machine based Classifiers on Biological Databases

Muhammad Amjad, Zulfiqar Ali, Abid Rafiq, Nadeem Akhtar, Israr-Ur-Rehman, Ali Abbas
2019 International Journal of Advanced Computer Science and Applications  
This paper focuses on the problem of selection of more efficient, promising and suitable classifier for the prediction of specific diseases by performing empirical studies on bunch mark medical databases  ...  This research work provides the empirical performance analysis of decision tree-based classifiers and SVM on a specific dataset.  ...  So avoid by overfitting, many decision tree algorithm used the pruning method. In this method, growing the decision is stopped while deleting the portions of the tree.  ... 
doi:10.14569/ijacsa.2019.0100940 fatcat:ekopo2ll6zgnjdqg4xpqqyz46q
« Previous Showing results 1 — 15 out of 390 results