#### DMCA

## Top 10 algorithms in data mining (2007)

### Cached

### Download Links

- [www.cse.ust.hk]
- [www.cs.uvm.edu]
- [www.ideal.ece.utexas.edu]
- [www.cs.umd.edu]
- [storm.cis.fordham.edu]
- [www.cs.ust.hk]
- [www.maths.uq.edu.au]
- [www2.cs.uh.edu]
- [www2.cs.uh.edu]
- [www.cse.ust.hk]
- [143.89.40.4]
- [www.cs.indiana.edu]
- [cs.nju.edu.cn]
- [www.cs.uvm.edu]
- [www.cse.ust.hk]
- [www.cs.umd.edu]
- [www.maths.uq.edu.au]
- [storm.cis.fordham.edu]
- [www.ar.sanken.osaka-u.ac.jp]

Citations: | 113 - 2 self |

### Citations

12894 | Statistical Learning Theory
- Vapnik
- 1998
(Show Context)
Citation Context ...ave ensured its continued relevance and gradually increased its effectiveness as well. 3 Support Vector Machines by Qiang Yang4 In today’s machine learning applications, support vector machines (SVM) =-=[66]-=- are considered a must try - it offers one of the most robust and accurate methods among all well-known algorithms. It has a sound theoretical foundation, requires only a dozen examples for training, ... |

11694 | Maximum likelihood from incomplete data via the em algorithm
- Dempster, Laird, et al.
- 1977
(Show Context)
Citation Context ... a @ ® O ff [ > J ? º ¢ E X @ i J¯® O (6) is the log likelihood function for ® . Solutions of (6) corresponding to local maximizers can be obtained via the expectation-maximization (EM) algorithm =-=[13]-=-. For the modeling of continuous data, the component-conditional densities are usually taken to belong to the same parametric family, for example, the normal. In this case, X @ i J ° O ff~ @ i ... |

5792 |
Classification and Regression Trees
- BREIMAN, FRIEDMAN, et al.
- 1984
(Show Context)
Citation Context ... when this appears beneficial the tree is modified accordingly. The pruning process is completed in one pass through the tree. C4.5’s tree-construction algorithm differs in several respects from CART =-=[7]-=-, for instance: Tests in CART are always binary, but C4.5 allows two or more outcomes. CART uses the Gini diversity index to rank tests, whereas C4.5 uses information-based criteria. CART prunes... |

4581 | The anatomy of a large-scale hypertextual web search engine
- Brin, Page
(Show Context)
Citation Context ...41]. Alternatively, one can apply BIC, which leads to the selection of E ff E over E ff EjÇ if L d log È is greater than log @ H O . 6 PageRank by Bing Liu and Philip S. Yu7 6.1 Overview PageRank =-=[8]-=- was presented and published by Sergey Brin and Larry Page at the Seventh International World Wide Web Conference (WWW7) in April, 1998. It is a search ranking algorithm using hyperlinks on the Web. B... |

3536 | Fast Algorithms for Mining Association Rules
- Agrawal, Srikant
- 1994
(Show Context)
Citation Context ...ward to generate association rules with confidence larger than or equal to a user specified minimum confidence. Apriori is a seminal algorithm for finding frequent itemsets using candidate generation =-=[1]-=-. It is characterized as a level-wise complete search algorithm using anti-monotonicity of itemsets, “if an itemset is not frequent, any of its superset is never frequent”. By convention, Apriori assu... |

3403 | A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
- Freund, Schapire
- 1997
(Show Context)
Citation Context ...C5.0 C4.5 was superseded in 1997 by a commercial system See5/C5.0 (or C5.0 for short). The changes encompass new capabilities as well as much-improved efficiency, and include: A variant of boosting =-=[20]-=-, which constructs an ensemble of classifiers that are then voted to give a final classification. Boosting often leads to a dramatic improvement in predictive accuracy. New data types (eg, dates), “... |

3201 | Rapid object detection using a boosted cascade of simple features
- Viola, Jones
- 2001
(Show Context)
Citation Context ...ne of the most prestigious awards in theoretical computer science, in the year of 2003. AdaBoost and its variants have been applied to diverse domains with great success. For example, Viola and Jones =-=[67]-=- combined AdaBoost with a cascade process for face detection. They regarded rectangular features as weak learners, and by using AdaBoost to weight the weak learners, they got very intuitive features f... |

3176 | The pagerank citation ranking: Bringing order to the web
- Page, Brin, et al.
- 1999
(Show Context)
Citation Context ...vector of all 1’s. This gives us the PageRank formula for each page # : @ # O ff @ %1LM O U× [ > J ? sØJ @ © O (16) which is equivalent to the formula given in the original PageRank papers =-=[8, 47]-=-: @ # O ff @ %1LÆ O U× > Á JnÎ ÃÐÏFÑ @ © O Ò J ( (17) The parameter is called the damping factor which can be set to a value between 0 and 1. = 0.85 is used in [8, 39]. 17 ÙºÚFÛ Ü¯Ý-ÞFßàA... |

1689 | Mining frequent patterns without candidate generation
- Han, Pei, et al.
- 2000
(Show Context)
Citation Context ...mation required for computing support. The most outstanding improvement over Apriori would be a method called FP-growth (frequent 12 pattern growth) that succeeded in eliminating candidate generation =-=[30]-=-. It adopts a divide and conquer strategy by 1) compressing the database representing frequent items into a structure called FP-tree (frequent pattern tree) that retains all the essential information ... |

1343 |
Nearest neighbor pattern classification
- Cover, Hart
- 1967
(Show Context)
Citation Context ...ification is an easy to understand and easy to implement classification technique. Despite its simplicity, it can perform well in many situations. In particular, a well known result by Cover and Hart =-=[11]-=- shows that the the error of the nearest neighbor rule is bounded above by twice the Bayes error under certain reasonable assumptions. Also, the error of the general kNN method asymptotically approach... |

1309 |
A probabilistic Theory of Pattern Recognition., volume 31 of Applications of Mathematics
- Devroye, Györfi, et al.
- 1996
(Show Context)
Citation Context ...f work addressing these threes areas and indicate some remaining open problems. Other important resources include the collection of papers by Dasarathy [12] and the book by Devroye, Gyorfi and Lugosi =-=[14]-=-. Finally, a fuzzy approach to kNN can be found in the work of Bezdek [3]. 9 Naive Bayes by David J. Hand10 9.1 Introduction Given a set of objects, each of which belongs to a known class, and each of... |

1042 |
Introduction to Data Mining
- Tan, Steinbach, et al.
- 2005
(Show Context)
Citation Context ...of this approach is that many test records will not be classified because they do not exactly match any of the training records. A more sophisticated approach, k-nearest neighbor (kNN) classification =-=[19, 60]-=-, finds a group of k objects in the training set that are closest to the test object, and bases the assignment of a label on the predominance of a particular class in this neighborhood. There are thre... |

1013 |
Social Network Analysis
- Wasserman, Faust
- 1994
(Show Context)
Citation Context ...at casts the vote. Votes casted by pages that are themselves “important” weigh more heavily and help to make other pages more “important”. This is exactly the idea of rank prestige in social networks =-=[69]-=-. 6.2 The Algorithm We now introduce the PageRank formula. Let us first state some main concepts in the Web context. In-links of page i: These are the hyperlinks that point to page i from other pages.... |

926 | Improved boosting algorithms using confidence-rated predictions - Schapire, Singer - 1999 |

799 | On the optimality of the simple Bayesian classifier under zero-one loss
- Domingos, Pazzani
- 1997
(Show Context)
Citation Context ... in any particular application, but it can usually be relied on to be robust and to do quite well. General discussion of the naive Bayes method and its merits are given in Domingos and Pazzani (1997) =-=[18]-=- and Hand and Yu (2001) [27]. 9.2 The Basic Principle For convenience of exposition here, we will assume just two classes, labeled #ff ]l% . Our aim is to use the initial set of objects with known ... |

780 | Bayesian network classifiers
- Friedman, Geiger, et al.
- 1997
(Show Context)
Citation Context ...recognize that such modifications are necessarily complications, which detract from its basic simplicity. Some such modifications are described in Ridgeway et al (1998) [52] and Friedman et al (1997) =-=[23]-=-. 25 10 CART by Dan Steinberg11 The 1984 monograph, “CART: Classification and Regression Trees,” co-authored by Leo Breiman, Jerome Friedman, Richard Olshen, and Charles Stone, [7] represents a major ... |

751 | An algorithm for finding best matches in logarithmic expected time
- Friedman, Bentley, et al.
- 1977
(Show Context)
Citation Context ... applied to new data that does include missing values. This is in contrast to machines that can only learn about missing value handling from training data that include missing values. Friedman (1975) =-=[21]-=- suggests moving instances with missing splitter attributes into both left and right child nodes and making a final class assignment by pooling all nodes in which an instance appears. Quinlan (1989) [... |

632 | DB: Maximum likelihood from incomplete data via EM algorithm - AP, NM, et al. - 1977 |

632 | gSpan: Graph-based substructure pattern mining
- Yan, Han
- 2002
(Show Context)
Citation Context ...tly. AprioriSMP uses this principle [45]. 5) using richer expressions than itemset: Many algorithms have been proposed for sequences, tree and graphs to enable mining from more complex data structure =-=[73, 35]-=-. 6) closed itemsets: A frequent itemset is closed if it is not included in any other frequent itemsets. Thus, once the closed itemsets are found, all the frequent itemsets can be derived from them. L... |

599 | A comparison of document clustering techniques
- Steinbach, Karypis, et al.
(Show Context)
Citation Context ... 6 then identifies the which minimizes this adjusted cost. Alternatively, one can progressively increase the number of clusters, in conjunction with a suitable stopping criterion. Bisecting k-means =-=[59]-=- achieves this by first putting all the data into a single cluster, and then recursively splitting the least compact cluster into two using 2-means. The celebrated LBG algorithm [28] used for vector q... |

576 | Agrawal: Mining Generalized Association Rules
- Srikant, R
- 1996
(Show Context)
Citation Context ...r than the original Apriori algorithm. There are several other dimensions regarding the extensions of frequent pattern mining. The major ones include the followings. 1) incorporating taxonomy in items=-=[58]-=-: Use of taxonomy makes it possible to extract frequent itemsets that are expressed by higher concepts even when use of the base level concepts produces only infrequent itemsets. 2) incremental mining... |

435 | Clustering with Bregman divergences
- Banerjee, Merugu, et al.
- 2005
(Show Context)
Citation Context ...an divergences during the assignment step and makes no other changes, the essential properties of k-means, including guaranteed convergence, linear separation boundaries and scalability, are retained =-=[2]-=-. This result makes k-means effective for a much larger class of datasets so long as an appropriate divergence is used. k-means can be paired with another algorithm to describe non-convex clusters. On... |

413 |
Discriminatory analysis, nonparametric discrimination: consistency properties
- Fix, Hodges
- 1951
(Show Context)
Citation Context ...of this approach is that many test records will not be classified because they do not exactly match any of the training records. A more sophisticated approach, k-nearest neighbor (kNN) classification =-=[19, 60]-=-, finds a group of k objects in the training set that are closest to the test object, and bases the assignment of a label on the predominance of a particular class in this neighborhood. There are thre... |

410 | Metacost: a general method for making classifiers cost-sensitive
- Domingos
- 1999
(Show Context)
Citation Context ...been included in the released software. 10.7 Cost-Sensitive Learning Costs are central to statistical decision theory but cost-sensitive learning received only modest attention before Domingos (1999) =-=[17]-=-. Since then, several conferences have been devoted exclusively to this topic and a large number of research papers have appeared in the subsequent scientific literature. It is therefore useful to not... |

330 |
The Condensed Nearest Neighbor Rule
- Hart
- 1968
(Show Context)
Citation Context ...eliminate many of the stored data objects, but still retain the classification accuracy of the kNN classifier. This is known as ‘condensing’ and can greatly speed up the classification of new objects =-=[29]-=-. In addition, data objects can be removed to improve classification accuracy, a process known as ‘editing’ [71]. There has also been a considerable amount of work on the application of proximity grap... |

304 | A weighted nearest neighbor algorithm for learning with symbolic features
- Cost, Salzberg
- 1993
(Show Context)
Citation Context ...e assigned to the training objects themselves. This can give more weight to highly reliable training objects, while reducing the impact of unreliable objects. The PEBLS system by by Cost and Salzberg =-=[10]-=- is a well known example of such an approach. KNN classifiers are lazy learners, that is, models are not built explicitly unlike eager learners (e.g., decision trees, SVM, etc.). Thus, building the mo... |

238 | C4.5: programs for machine learning - JR - 1993 |

226 | Kernel k-means: spectral clustering and normalized cuts
- Dhillon, Guan, et al.
- 2004
(Show Context)
Citation Context ...ters are updated to best fit the assigned datasets. Such modelbased k-means allow one to cater to more complex data, e.g. sequences described by Hidden Markov models. One can also “kernelize” k-means =-=[15]-=-. Though boundaries between clusters are still linear in the implicit high-dimensional space, they can become non-linear when projected back to the original space, thus allowing kernel k-means to deal... |

221 | Maintenance of discovered association rules in large databases: An incremental updating technique
- Cheung, Han, et al.
- 1996
(Show Context)
Citation Context ...l concepts produces only infrequent itemsets. 2) incremental mining: In this setting, it is assumed that the database is not stationary and a new instance of transaction keeps added. The algorithm in =-=[9]-=- updates the frequent itemsets without restarting from scratch. 3) using numeric valuable for item: When the item corresponds to a continuous numeric value, current frequent itemset mining algorithm i... |

198 | Optimal multi-step k-nearest neighbor search - Seidl, Kriegel - 1998 |

197 |
Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data (Data-Centric Systems and Applications
- Liu
- 2006
(Show Context)
Citation Context ...inal PageRank papers [8, 47]: @ # O ff @ %1LÆ O U× > Á JnÎ ÃÐÏFÑ @ © O Ò J ( (17) The parameter is called the damping factor which can be set to a value between 0 and 1. = 0.85 is used in =-=[8, 39]-=-. 17 ÙºÚFÛ Ü¯Ý-ÞFßàAá5âIãCänånæ çCèéZêyë ì í ← î3ïÐð ñ ← ò ó¯ôõön÷ ø ù úûü ý þ ß +−← ←ss fiff flffi! #"$&%('*)fi+(,!- ε . / 0 1 2 354 6 Figure 4: The power iterati... |

160 | The reduced nearest neighbor rule - Gates - 1972 |

152 | Experiments in induction - Hunt, Marin, et al. - 1966 |

120 | Unknown attribute values in induction
- Quinlan
- 1989
(Show Context)
Citation Context ...] suggests moving instances with missing splitter attributes into both left and right child nodes and making a final class assignment by pooling all nodes in which an instance appears. Quinlan (1989) =-=[49]-=- opts for a weighted variant of Friedman’s approach in his study of alternative missing value-handling methods. Our own assessments of the effectiveness of CART surrogate performance in the presence o... |

115 | Oblivious Decision Trees
- Kohavi, Li
- 1995
(Show Context)
Citation Context ...the presence of missing data are largely favorable, while Quinlan remains agnostic on the basis of the approximate surrogates he implements for test purposes [49]. In Friedman, Kohavi, and Yun (1996) =-=[22]-=-, Friedman notes that 50% of the CART code was devoted to missing value handling; it is thus unlikely that Quinlan’s experimental version properly replicated the entire CART surrogate mechanism. In CA... |

85 | 10 challenging problems in data mining research - Yang, Wu |

77 | Tibshirani R - Friedman, Hastie - 1998 |

71 | Text Categorization Using Weight Adjusted k-Nearest Neighbor Classification
- Han
- 1999
(Show Context)
Citation Context ...te the computation of distance and thus, the assignment of class labels. A number of schemes have been developed that try to compute the weights of each individual attribute based upon a training set =-=[26]-=-. In addition, weights can be assigned to the training objects themselves. This can give more weight to highly reliable training objects, while reducing the impact of unreliable objects. The PEBLS sys... |

60 | The EM algorithm and extensions - GJ, Krishnan - 1997 |

53 | Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28: 337–407 - JH, Hastie |

48 | Loan CF - GH, Van - 1989 |

28 | Interpretable Boosted Naive Bayes Classification
- Ridgeway, Madigan, et al.
- 1998
(Show Context)
Citation Context ... more flexible, but one has to recognize that such modifications are necessarily complications, which detract from its basic simplicity. Some such modifications are described in Ridgeway et al (1998) =-=[52]-=- and Friedman et al (1997) [23]. 25 10 CART by Dan Steinberg11 The 1984 monograph, “CART: Classification and Regression Trees,” co-authored by Leo Breiman, Jerome Friedman, Richard Olshen, and Charles... |

27 | Dubes RC - AK - 1988 |

26 | SVM feature selection for classification of spect images of alzheimer?s disease using spatial information - Stoeckel, Fung - 2005 |

21 | On bootstrapping the likelihood ratio test statistic for the number of components in a normal mixture. JAppl Stat - GJ - 1987 |

21 | Smola AJ (2002) Learning with Kernels - Scholkopf |

20 | The strength of weak learnability - RE - 1990 |

20 | Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat - RE, Freund, et al. - 1998 |

18 | Goldszmidt M - Friedman, Geiger - 1997 |

14 | Asymptotic properties of nearest neighbor rule using edited data - DL - 1972 |

13 | Nearest Neighbor NN Norms: NN Pattern Classification Techniques. Los Alamitos - BV - 1991 |

12 | An algorithm for finding best matches in logarithmic expected time [J - JH, JL, et al. - 1977 |

11 | CD (2006) Google’s PageRank and Beyond: The Science of Search Engine Rankings - AM, Meyer |

10 | Peel D 2000 Finite Mixture Models - GJ |

9 |
Probability Theory
- Breiman
- 1968
(Show Context)
Citation Context ...974. Leo Breiman earned his B.A. in Physics at the California Institute of Technology, his PhD in Mathematics at UC Berkeley, and made notable contributions to pure probability theory (Breiman, 1968) =-=[5]-=- while a Professor at UCLA. In 1967 he left academia for 13 years to work as an industrial consultant; during this time he encountered the military data analysis problems that inspired his contributio... |

8 | Lazy decision trees - JH, Kohavi, et al. - 1996 |

7 | Quality assessment of individual classifications in machine learning and data mining. Knowl Inf Syst 9(3):364–384 - Kukar - 2006 |

7 |
Generalized k-nearest neighbor rules, Fuzzy Sets and Systems 18
- Bedzek, Chuah
- 1986
(Show Context)
Citation Context ...lems. Other important resources include the collection of papers by Dasarathy [12] and the book by Devroye, Gyorfi and Lugosi [14]. Finally, a fuzzy approach to kNN can be found in the work of Bezdek =-=[3]-=-. 9 Naive Bayes by David J. Hand10 9.1 Introduction Given a set of objects, each of which belongs to a known class, and each of which has a known vector of variables, our aim is to construct a rule wh... |

6 | Quantization - RM, DL - 1998 |

6 | Karypis G (2005) Gene classification using expression profiles: a feasibility study - Kuramochi |

5 | Generalized k-nearest neighbor rules. Fuzzy Sets and Systems 18:237–256 - JC, SK, et al. - 1986 |

5 | Making clustering in delay-vector space meaningful. Knowl Inf Syst - JR - 2007 |

5 | The reduced nearest neighbor rule - GW - 1972 |

5 | Idiot’s Bayes—not so stupid after all? Int Stat Rev 2001;69:385–98 - DJ, Yu |

5 | Watanabe T (2007) Fast agglomerative hierarchical clustering algorithm using Locality-Sensitive Hashing. Knowl Inf Syst 12(1):25–53 - Koga, Ishibashi |

5 | An instance-weighting method to induce cost-sensitive trees - KM - 2002 |

5 | Takao Mohri - Wettschereck, Aha - 1997 |

4 | Lucchese C (2006) On condensed representations of constrained frequent patterns. Knowl Inf Syst 9(2):180–201 - Bonchi |

4 | Aono M (2006) Exploring overlapping clusters using dynamic re-scaling and sampling. Knowl Inf Syst 10(3):295–313 123 M. A. Hasan et al - Kobayashi |

4 | Discovering rules by induction from large collections of examples - JR - 1979 |

4 |
Risk Estimation for Classification Trees
- Bloch, Walker
- 2002
(Show Context)
Citation Context ...an adjustment 30 does not depend on the raw predicted probability in the node and the adjustment can be very small if the test data show that the tree is not overfit. Bloch, Olshen, and Walker (2002) =-=[4]-=- report very good performance for the Breiman adjustment in a series of empirical experiments. 10.10 Theoretical Foundations The earliest work on decision trees was entirely atheoretical. Trees were p... |

3 |
Prediction games and arcing classifiers. Neural Comput 11(7):1493
- Breiman
- 1999
(Show Context)
Citation Context ...nbased explanation. They argued that AdaBoost is able to increase the margins even after the training error is zero, and thus it does not overfit even after a large number of rounds. However, Breiman =-=[6]-=- indicated that larger margin does not necessarily mean better generalization, which seriously challenged the margin-based explanation. Recently, Reyzin and Schapire [51] found that Breiman considered... |

3 | PS, Muntz RR (2006) Catch the moment: maintaining closed frequent itemsets over a data stream sliding window. Knowl Inf Syst 10(3):265–294 - Chi, Wang, et al. |

3 | Agrawal G (2006) Fast and exact out-of-core and distributed k-means clustering. Knowl Inf Syst 10(1):17–40 - Jin, Goswami |

3 | Least squares quantization in PCM. Unpublished Bell Lab. Tech. Note, portions presented at the Institute of Mathematical statistics Meeting Atlantic City - SP - 1957 |

3 | A model search technique for predictive nominal scale multivariate analysis. J Am Stat Assoc 67:768–772 - RC, ML - 1972 |

3 | A conversation with Leo Breiman. Stat Sci 16(2):184–198 - Olshen - 2001 |

3 | Schapire RE (2006) How boosting the margin can also boost classifier complexity - Reyzin |

3 | Proximity graphs for nearest neighbor decision rules: recent progress - GT - 2002 |

3 | Open problems in geometric methods for instance-based learning - GT - 2002 |

3 | Cheung P-M (2005) Core vector machines: Fast SVM training on very large data sets - IW, JT |

3 | Arimura H (2004) An efficient algorithm for enumerating frequent closed patterns in transaction databases - Uno, Asai, et al. |

3 | B (2005) Adding the temporal dimension to search—a case study in publication search.In - PS, Li, et al. |

3 | Silvescu A, Honavar V (2006) Learning accurate and concise naïve Bayes classifiers from attribute value taxonomies and data. Knowl Inf Syst 9(2):157–179 - Zhang, Kang |

2 | Leng PH (2006) Tree-based partitioning of date for association rule mining. Knowl Inf Syst 10(3):315–331 - Ahmed, Coenen |

2 | MG (2002) Risk estimation for classification trees - DA, RA, et al. |

2 | Machine learning: Four current directions - TG - 1997 |

2 | T (2007) Non-redundant data clustering. Knowl Inf Syst 12(1):1–24 - Gondek, Hofmann |

2 | Graepel T, Obermayer K (2000) Rank boundaries for ordinal regression. Adv Mar Classif pp 115–132 - Herbrich |

2 | Sung SY (2006) Finding centroid clusterings with entropy-based criteria. Knowl Inf Syst 10(4):505–514 - Hu |

2 | Washio T, Motoda H (2005) General framework for mining frequent subgraphs from labeled graphs. Fundament Inform - Inokuchi |

2 | SC-f, Chung F-L (2006) A collaborative filtering framework based on fuzzy association rules and multiple-level similarity. Knowl Inf Syst 10(3):357–381 - CW-k, Chan |

2 | Ogihara M (2006) Using discriminant analysis for multi-class classification: an experimental investigation. Knowl Inf Syst 10(4):453–472 36 X. Wu et al - Li, Zhu |

2 | Hoque T (2007) CanTree: a canonical-order tree for incremental frequentpattern mining. Knowl Inf Syst 11(3):287–311 - CK-S, QI, et al. |

2 | Sese J (2000) Traversing lattice itemset with statistical metric pruning - Morishita |

2 | V (2007) Generalizing the notion of confidence. Knowl Inf Syst 12(3):279–299 - Steinbach, Kumar |

2 | Cowling PI, Peng Y (2006) Multiple labels associative classification. Knowl Inf Syst 9(1):109–129 - FA |

2 | Motoda H (2005) Association rules based on levelwise subspace clustering. In: Proceedings. of 9th European conference on principles and practice of knowledge discovery in databases - Washio, Nakanishi |

2 |
Dasarathy (editor). “Nearest neighbor (NN) norms: NN pattern classification techniques
- V
- 1991
(Show Context)
Citation Context ...proximity graph viewpoint, provide an overview of work addressing these threes areas and indicate some remaining open problems. Other important resources include the collection of papers by Dasarathy =-=[12]-=- and the book by Devroye, Gyorfi and Lugosi [14]. Finally, a fuzzy approach to kNN can be found in the work of Bezdek [3]. 9 Naive Bayes by David J. Hand10 9.1 Introduction Given a set of objects, eac... |

1 |
Dietterich,“Machine learning: Four current directions
- G
- 1997
(Show Context)
Citation Context ... Liu [39] and by Langville and Meyer [38] contain in-depth analyses of PageRank and several other link-based algorithms. 7 AdaBoost by Zhi-Hua Zhou8 7.1 Description of the Algorithm Ensemble learning =-=[16]-=- deals with methods which employ multiple learners to solve a problem. The generalization ability of an ensemble is usually significantly better than that of a single learner, so ensemble methods are ... |