{"references": ["Akhtar, M. T., Jung, T.-P., Makeig, S., and Cauwenberghs, G., 2012.\nRecursive independent component analysis for online blind source\nseparation, IEEE International Symposium on Circuits and Systems.", "Amari, S., Cichocki, A., and Yang, H.-H., 1996. A new learning\nalgorithm for blind signal separation, In Advances in Neural Information\nProcessing Systems, D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo,\nEditor, Vol.8, pp.757\u2013763, The MIT Press.", "Azoury, K. S., and Warmuth, M. K., 2001. Relative loss bounds for\non-line density estimation with the exponential family of distribution,\nMachine Learning, Vol.42, No.3, pp.211\u2013246.", "Banerjee, A., Merugu, S., Dhillon, I., and Ghosh, J., 2005. Clustering\nwith Bregman divergences, Journal of Machine Learning Research, Vol.\n6, pp.1705\u20131749.", "Banerjee, A., and Basu, S. 2007. Topic Models over Text Streams: A\nStudy of Batch and Online Unsupervised Learning, SIAM International\nConference on Data Mining.", "Bassiou, N. K., and Kotropoulos, C. L., 2014. Online PLSA:\nBatch Updating Techniques Including Out-of-Vocabulary Words, IEEE\nTransaction on Neural Networks and Learning Systems, Vol.25, Issue.11,\npp.1953\u20131966.", "Bell, A. J., and Sejnowski, T. J., 1997. An information-maximization\napproach to blind separation and blind dexonvolution, Neural\nComputation, Vol.7, pp.1129\u20131159.", "Blei, D. M., Ng, A. Y., and Jordan, M. I. 2003. Latent dirichlet\nallocation, The Journal of Machine Learning Research, Vol. 3, pp.\n993\u20131022.", "Blei, D. M. 2012. Probabilistic topic models, Commun. ACM, Vol. 55,\nNo. 4, pp. 77\u201384.\n[10] Brown, G., Pocock, A., Zhao, M-J., and Luj\u00b4an, M. 2012. Conditional\nlikelihood maximisation: A unifying framework for information\ntheoretic feature, Journal of Machine Learning Research (JMLR), Vol.\n13, pp. 27\u201366.\n[11] Chien, J.-T., and Wu, M.-S., 2007. Adaptive Bayesian Latent\nSemantic Analysis, IEEE Transactions on Audio, Speech and Language\nProcessing, Vol.16, Issue.1, pp.198\u2013207.\n[12] Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and\nHarshman, R. 1990. Indexing by latent semantic analysis, Journal of the\nAmerican Society of Information Science, Vol. 41, No. 6, pp. 391\u2013407.\n[13] Elkan, C., 2006. Clustering documents with an exponential-family\napproximation of the Dirichlet compund multinomial distribution, In\nProceedings of the 23rd International Conference on Machine Learning.\n[14] Hertz, J., Krogh, A., and Palmer, R. G., 1991. Introduction To the Theory\nof Neural Computation, Addison-Wesley, Reading, MA.\n[15] Hofmann, T. 1999. Probabilistic latent semantic analysis, Proceedings\nof the 15th Conference on Uncertainty in Artificial Intelligence (UAI'99),\npp. 289\u201329, Morgan Kaufmann Publishers Inc..\n[16] Hyv\u00a8arinen A. 1999. Fast and robust fixed-point algorithms for\nindependent component analysis, IEEE Trans. on Neural Networks,\nVol. 10, No. 3.\n[17] Hyv\u00a8arinen, A., Karhunen, J. and Oja, E. 2001. Independent component\nanalysis, John Wiley & Sons.\n[18] Lichman, M. 2013. UCI machine learning repository,\nhttp://archive.ics.uci.edu/ml , Accessed on 11/11/2016.\n[19] Madsen, R., Kauchak, D., and Elkan, C., 2005. Modeling word\nburstiness using the Dirichlet distribution, In Proceedings of the 22nd\nInternational Conference on Machine Learning.\n[20] Neal, R.M., and Hinton, G.E., 1998. A view of the EM algorithm that\njustifies incremental, sparse, and other variants. In M.I. Jordan, editor,\nLearning in Graphical Model, pp.355\u2013368, MIT Press.\n[21] Oja, E., and Karhunen, J., 1985. On stochastic approximation of the\neigenvectors and eigenvalues of the expectation of a random matrix,\nJournal of Mathematical Analysis and Application, Vol.106, pp.69\u201384.\n[22] Salton, G., Fox, E. A., Wu, H. 1983. Extended boolean information\nretrieval, Commun. ACM, Vol. 26, No. 11, pp. 1022\u20131036.\n[23] Sanger, T. D., 1989. Optimal unsupervised learning in a single-layer\nlinear feedforward neural network, IEEE Transaction on Neural\nNetworks, Vol.2, pp. 459\u2013473.\n[24] Schraudolph, N. N., and Giannakopoulos, X., 1999. Online Independent\nComponent Analysis With Local Learning Rate Adaptation, NIPS, pp.\n789\u2013795\n[25] Shinohara, Y. 1999. Independent Topic Analysis : Extraction of\nCharacteristic Topics by maximization of Independence, Technical report\nof IEICE.\n[26] Shinohara, Y. 2000. Development of Browsing Assistance System for\nfinding Primary Topics and Tracking their Changes in a Document\nDatabase, CRIEPI Research Report.\n[27] Sirovich, I., and Kirby, M., 1987. Low-Dimensional procedure for the\ncaracterization of human faces, Journal of Optical Society of America\nA, Vol.4, No.3, pp.519\u2013524.\n[28] Song, X., Lin, C.-Y., Tseng, B. L., Sun, M.-T., 2005. Modeling and\npredicting personal information dissemination behavior, In Proceedings\nof the 11th ACM SIGKKD International Conference on Knowledge\nDiscovery and Data Mining.\n[29] Tanaka, M, Shinohara, Y. 2003. Topic-Based Dynamic Document\nManagement System for discovering Important and New Topics, CRIEPI\nResearch Report.\n[30] Weng, J., Zhang, Y, and Hwang, W.-S., 2003. Candid Covariance-free\nIncremental Principal Compoenent Aalysis, IEEE Transaction on Pattern\nAnalysis and Machine Intelligence, Vol.25, No.8, pp.1034\u20131040.\n[31] Zhao, Y. and Karypis, G. 2002. Evaluation of hierarchical clustering\nalgorithms for document datasets, Conference of Information and\nKnowledge Management (CIKM), pp. 515\u2013524, ACM. [32] Zhong, S., and Ghosh, J. 2003. A comparative study of generative\nmodels for document clustering, Data Mining Workshop on Clustering\nHigh Dimensional Data and Its Applications."]}

In this paper, we present a method of applying Independent Topic Analysis (ITA) to increasing the number of document data. The number of document data has been increasing since the spread of the Internet. ITA was presented as one method to analyze the document data. ITA is a method for extracting the independent topics from the document data by using the Independent Component Analysis (ICA). ICA is a technique in the signal processing; however, it is difficult to apply the ITA to increasing number of document data. Because ITA must use the all document data so temporal and spatial cost is very high. Therefore, we present Incremental ITA which extracts the independent topics from increasing number of document data. Incremental ITA is a method of updating the independent topics when the document data is added after extracted the independent topics from a just previous the data. In addition, Incremental ITA updates the independent topics when the document data is added. And we show the result applied Incremental ITA to benchmark datasets.