Home Research CV

Pavel Kuksa

Publications:

Journal Publications
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Efficient use of unlabeled data for protein sequence classification: a comparative study. BMC Bioinformatics, 10(Suppl 4):S2, 2009. Impact factor: 3.78
  Details     BibTeX    [pdf] (173.3kB )  [URL] 
• Pavel Kuksa and Vladimir Pavlovic. Efficient alignment-free DNA barcode analytics. BMC Bioinformatics, 10(Suppl 14):S9, 2009. Impact factor: 3.78
  Details     BibTeX    [pdf] (1.8MB )  [URL]  [Supplementary Material]
• Pavel Kuksa and Vladimir Pavlovic. Efficient motif finding algorithms for large-alphabet inputs. BMC Bioinformatics, 11(Suppl 8):S1, 2010.
  Details     BibTeX    [pdf] (597.3kB )  [URL] 
• Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. Natural Language Processing (Almost) from Scratch. Journal of Machine Learning, 12:2493–2537, 2011.
  Details     BibTeX    [pdf] (414.8kB )  

Top conferences
• Pavel P. Kuksa, Imdadullah Khan, and Vladimir Pavlovic. Generalized Similarity Kernels for Efficient Sequence Classification. In SDM, 2012.
  Details     BibTeX    [pdf] (315.8kB )  
• Pavel Kuksa and Yanjun Qi. Semi-Supervised Bio-Named Entity Recognition with Word-Codebook Learning. In SDM, 2010. Acceptance rate: 82/351 (23%)
  Details     BibTeX    [pdf] (394.1kB )  
• Pavel P. Kuksa, Yanjun Qi, Bing Bai, Ronan Collobert, Jason Weston, Vladimir Pavlovic, and Xia Ning. Semi-Supervised Abstraction-Augmented String Kernel for Multi-Level Bio-Relation Extraction. In ECML, 2010. Acceptance rate: 106/658 (16%)
  Details     BibTeX    [pdf] (199.4kB )  
• Yanjun Qi, Ronan Collobert, Pavel Kuksa, Koray Kavukcuoglu, and Jason Weston. Combining labeled and unlabeled data with word-class distribution learning. In Proceeding of the 18th ACM Conference on Information and Knowledge Management CIKM 2009, pp. 1737–1740, 2009. Acceptance rate: (123+171)/847 (20% short paper)
  Details     BibTeX    [pdf] (142.2kB )  [URL] 
• Yanjun Qi, Pavel P. Kuksa, Ronan Collobert, Kunihiko Sadamasa, Koray Kavukcuoglu, and Jason Weston. Semi-Supervised Sequence Labeling with Self-Learned Features. In Proc. International Conference on Data Mining (ICDM'09), IEEE, 2009. Acceptance rate: 8.9% regular (70/786)
  Details     BibTeX    [pdf] (231.8kB )  
• Pavel P. Kuksa and Vladimir Pavlovic. Efficient Motif Finding Algorithms for Large-Alphabet Inputs. In BIOKDD, 2010. Acceptance rate: 7/29 regular (24%)
  Details     BibTeX    [pdf] (442.7kB )  
• Pavel Kuksa and Vladimir Pavlovic. Fast motif selection for biological sequences. In IEEE International Conference on Bioinformatics and Biomedicine BIBM'09, 2009. Acceptance rate: (44+37)/233 (35%)
  Details     BibTeX    [pdf] (159.6kB )  [URL] 
• Pavel P. Kuksa and Vladimir Pavlovic. Spatial Representation for Efficient Sequence Classification. In ICPR, 2010. Acceptance rate: 385/2140 oral (18%)
  Details     BibTeX    [pdf] (144.0kB )  
• Pavel Kuksa and Vladimir Pavlovic. Efficient Alignment-free Barcode Analytics. In Third International Barcode of Life Conference, 2009.
  Details     BibTeX    [URL] 
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Scalable Algorithms for String Kernels with Inexact Matching. In NIPS, 2008. Spotlight Presentation. Acceptance rate: 123/1022 (12%)
  Details     BibTeX    [pdf] (111.0kB )  [supplementary data]
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. On the role of local matching for efficient semi-supervised protein sequence classification. In BIBM, 2008. Acceptance rate: 38/156 (24%)
  Details     BibTeX    [pdf] (133.0kB )  
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. A fast, semi-supervised learning method for protein sequence classification. In 8th International Workshop on Data Mining in Bioinformatics (BIOKDD 2008), pp. 29–37, 2008. Acceptance rate: 8/25 (32%)
  Details     BibTeX    [pdf] (197.0kB )  
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Fast and Accurate Multi-class Protein Fold Recognition with Spatial Sample Kernels. In Computational Systems Bioinformatics: Proceedings of the CSB2008 Conference, pp. 133–143, 2008. Acceptance rate: 30/135 (22%)
  Details     BibTeX    [pdf] (399.1kB )   [supplementary materials]
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Fast Protein Homology and Fold Detection with Sparse Spatial Sample Kernels. In 19th International Conference on Pattern Recognition ICPR 2008, 2008. Acceptance rate: 18% (oral). Best paper nominee
  Details     BibTeX    [pdf] (89.0kB )  [supplementary materials]
• Pavel Kuksa and Vladimir Pavlovic. Fast Barcode-Based Species Identification Using String Kernels. In Second International Barcode of Life Conference, 2007. Acceptance rate: 30% (oral)
  Details     BibTeX    [URL] 
• Pavel Kuksa and Vladimir Pavlovic. Fast Kernel Methods for SVM Sequence Classifiers. In WABI, pp. 228–239, 2007. Acceptance rate: 37/131 (28%)
  Details     BibTeX    [pdf] (145.2kB )  

Workshop papers

• Pavel Kuksa and Vladimir Pavlovic. Efficient evaluation of large sequence kernels. In NYAS Machine Learning Symposium, 2011.
  Details     BibTeX    [pdf] (203.4kB )  
• Pavel Kuksa and Vladimir Pavlovic. Efficient Sequence Classification with Spatial Representations. In Snowbird Learning Workshop, April 2010. Oral presentation.
  Details     BibTeX    [pdf] (22.9kB )  
• Vladimir Pavlovic and Pavel Kuksa. Large scale sequence analytics. In Center for Dynamic Data Analytics (CDDA) Workshop (January 25-26, 2010), 2010.
  Details     BibTeX    [URL] 
• Jason Weston, Ronan Collobert, Frederic Ratle, Hossein Mobahi, Pavel Kuksa, and Koray Kavukcuoglu. Deep Learning via Semi-Supervised Embedding. In ICML 2009 Workshop on Learning Feature Hierarchies, 2009.
  Details     BibTeX    [URL] 
• Pavel Kuksa and Vladimir Pavlovic. Efficient Discovery of Common Patterns in Sequences. Snowbird Learning Workshop, Clearwater, Florida, April 13-16 2009, 2009.
  Details     BibTeX    [pdf] (100.8kB )  
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. High Performance Sequence Classification with Novel Spatial Sample Embedding. 3rd Annual Machine Learning Symposium, NY, Oct 10, 2008, 2008.
  Details     BibTeX    [URL] 
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Spatially-constrained sample kernel for sequence classification. Snowbird Learning Workshop, Utah, April 1-4, 2008, 2008.
  Details     BibTeX    [pdf] (38.6kB)  [poster]
• Pavel Kuksa and Vladimir Pavlovic. Kernel methods for DNA barcoding. Snowbird Learning Workshop, San Juan, Puerto Rico, March 2007, 2007.
  Details     BibTeX    [URL] 

Tech Reports

• Pavel Kuksa and Vladimir Pavlovic. Efficient discovery of common patterns in sequences over large alphabets. Technical Report 2009-15, DIMACS, 2009.
  Details     BibTeX    [pdf] (395.2kB )  
• Pavel Kuksa, Pai-Hsi Huang, and Vladimir Pavlovic. Kernel Methods and Algorithms for General Sequence Analysis. Technical Report DCS-TR-630, Rutgers University, 2008.
  Details     BibTeX    [URL] 
• Pai-Hsi Huang, Pavel Kuksa, and Vladimir Pavlovic. Fast and accurate semi-supervised protein homology detection with large uncurated sequence databases. Technical Report RU-DCS-TR634, Rutgers University, 2008.
  Details     BibTeX    [pdf] (218.6kB )  
• Robert S. Moore, Richard Howard, Pavel Kuksa, and Richard P. Martin. A Geometric Approach to Device-Free Motion Localization Using Signal Strength. Technical Report DCS-TR-674, Rutgers University, 2010.
  Details     BibTeX    [pdf] (456.2kB )  
• Ronan Collobert, Jason Weston, Leon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. Natural Language Processing (almost) from Scratch. arXiv:1103.0398v1, 2011.
  Details     BibTeX    [pdf] (726.8kB )  
• Pavel P. Kuksa, Imdadullah Khan, and Vladimir Pavlovic. Generalized Similarity Kernels for Efficient Sequence Classification. Technical Report RU-DCS-TR684, Rutgers University, 2011.
  Details     BibTeX    [pdf] (164.2kB )  

Theses

• Pavel P. Kuksa. Scalable Kernel Methods and Algorithms for General Sequence Analysis. Ph.D. Thesis, 2011 [pdf]
  Dissertation Committee: Vladimir Pavlovic, Casimir Kulikowski, Alexander Schliep, Christina Leslie

Invited Talks

• Pavel Kuksa and Vladimir Pavlovic. String kernel-based species identification using DNA barcodes. Joint Molecular Biosciences Symposium, Feb 29, 2008, 2008.
  Details     BibTeX    [URL] 
• Pavel Kuksa and Vladimir Pavlovic. Kernel Methods for DNA Barcoding. Rutgers Bioinformatics Meeting, Nov 11, 2006, 2006.
  Details     BibTeX    [pdf] (634.1kB )  

Other Presentations

• Pavel P. Kuksa. Scalable Kernel Methods and Algorithms for General Sequence Analysis. Ph.D. Defense, March 30, 2011 [pdf]
• Pavel P. Kuksa. Scalable Kernel Methods and Algorithms for General Sequence Analysis. Ph.D. Predefense, Oct 19, 2010 [pdf]
• Pavel Kuksa. Kernel Methods and Algorithms for General Sequence Analysis. Ph.D. Qualifying Exam Presentation [pdf]

Publications in Russian

• Kouxa, Pavel. "Applications of Associative Memory and Associative Processors in Network Devices: A Survey." (Primenenie associativnih ZU i processorov v setevih ustroistvah) Modern Information Technologies. Moscow: BMSTU Press, 2001. 20-24, ISBN 5-7038-2083-9 [pdf]
• Kouxa, Pavel. "Data Clustering with Neural Networks." (Primenenie neironnih setei dlya klasterizatsii dannih) Modern Information Technologies. Moscow: BMSTU Press, 2001. 7-13, ISBN 5-7038-2083-9 [pdf]
• Kouxa, Pavel. "Finding Logically Independent Operators Matrix." (Algoritm nahojdeniya matricy logicheskoi nesovmestimosti) Informatics and Control Systems in 21st century. Moscow: Eliks+ Press, 2002. 195-97, ISBN 5-93991-010-6 [pdf]
• Kouxa, Pavel. "Fuzzy Systems Simulation Software at Algorithmic Level." (Sistema modelirovaniya nechetkih system na algoritmicheskom urovne) Informatics and Control Systems in 21st century. Moscow, 2002. 201-04, ISBN 5-93991-010-6 [pdf]
• Kouxa, Pavel. "Finding Logically Independent Operators for Parallel Computations Scheduling." (Vychislenie matritsy logicheskoi nesovmestimosti pri organizatsii parallel'nyh vychislenii) Young Scientists, Graduate and Undergraduate Students Conference. Moscow: BMSTU Press, 2003. 293-97, ISBN 5-7038-2347-1 [pdf]
• Kouxa, Pavel. "Fuzzy Clustering Algorithm: Reducing Complexity." (Analiz algoritma nechetkoi klasterizatsii) Young Scientists, Graduate and Undergraduate Students Conference. Moscow: BMSTU Press, 2003. 249-53, ISBN 5-7038-2347-1 [pdf]
• Kouxa, Pavel. "Fuzzy Systems Definition Language." (Yazyk opisaniya nechetkih sistem) Journal of Volzskiy Tatishev University, Information Science Series.5 (2004): 92-97. [pdf]
• Kouxa, Pavel. "Linguistic Fuzzy Models Structure Identification and Optimization." (Strukturnaya identificatsiya i opptimizatsiya lingvisticheskih nechetkih modelei) Modern Information Technologies. Moscow: Eliks+, 2003. 7-16, ISBN 5-93991-014-9 [pdf]
• Kouxa, Pavel. "Neuro-Fuzzy Models: Analysis and Applications." (Analiz neiro-nechetkih modelei) Journal of Volzskiy Tatishev University, Information Science Series.5 (2004): 69-76. [pdf]
• Kouxa, Pavel. "Software Implementation of Fuzzy Logic Controllers." (Programmnaua realizatsiya nechetcih kontrollerov) Modern Information Technologies. Moscow: Eliks+, 2003. ISBN 5-93991-014-9 [pdf]
• Kouxa, Pavel. "Type-2 Fuzzy Models." (Nechetkie lingvisticheskie modeli vtorogo roda) Journal of Volzskiy Tatishev University, Information Science Series.5 (2004): 114-20. [pdf]
• Kouxa, Pavel. "Type-2 Fuzzy Sets Algebra." (Issledovanie operacii algebry nechetkih mnojestv vtorogo poryadka) Young Scientists, Graduate and Undergraduate Students Conference, Informatics and Control Systems. Moscow: BMSTU Press, 2003. 243-48, ISBN 5-7038-2347-1 [pdf]
• Kouxa, Pavel. "Approximation Accuracy of Fuzzy Systems." (Obespechenie tochnosti v nechetkih sistemah) Young Scientists, Graduate and Undergraduate Students Conference. Informatics and Control Systems in 21st century. Moscow: BMSTU Press, 2004. 152-156, ISBN 5-7038-2646-4 [pdf]
• Kouxa, Pavel. "Design Optimization of Non-Local Neuro-Fuzzy Models." (Optimizatsiya i sintez nelokal'nyh lingvisticheskih neiro-nechetkih modelei) Inter-universities Scientific and Technical Conference on �Modern Information Technologies�. Moscow, 2004. (in press) [pdf]
• Kouxa, P. "Fuzzy Systems: Learning and Self-Organization Methods." Young Scientists, Graduate and Undergraduate Students Conference. Informatics and Control Systems in 21st century. Moscow: BMSTU Press, 2004. 148-52, ISBN 5-7038-2646-4 [pdf]
• Kouxa Pavel, Schmakov E., Yahina I., Panushkin M. "A Survey on Supercomputing: Modern State and Perspectives." (Superkomputery: sostoyanie i perspektivy) Anniversary Inter-universities Scientific and Technical Conference on "Modern Information Technologies". Moscow: BMSTU Press, 2000. 61-68, ISBN 5-7038-1752-8 [pdf]
• Timofeev V.V., Kouxa P. "Design and Identification of Fuzzy Models in Control and Systems Modeling." (Postroenie i identifikatsiya nechetkih modelei v prilojeniyah upravlenia i sistemnogo modelirovaniya) First International Conference "Aerospace Technologies". Moscow: BMSTU Press, 2004. ISBN 5-7038-2517-2 [pdf]

Conferences:

International Conferences

• First International Conference 'Aerospace Technologies', Moscow , May 2004.

Russian Conferences

• Annual Inter-universities Scientific and Technical Conference on Modern Information Technologies, Moscow, November 2004.
• Young Scientists, Graduate and Undergraduate Students Conference 'Informatics and Control Systems in 21st Century', Moscow, May 2004.
• Annual Inter-universities Scientific and Technical Conference on Modern Information Technologies, Moscow, November 2003.
• Young Scientists, Graduate and Undergraduate Students Conference 'Informatics and Control Systems', Moscow, May 2003.
• Students' Scientific Conference 'Informatics and Control Systems in 21st Century', Moscow, May 2002.
• Annual Inter-universities Scientific and Technical Conference on Modern Information Technologies, Moscow, November 2001.
• Anniversary Inter-universities Scientific and Technical Conference on Modern Information Technologies, Moscow, November 2000.