PAPERS

Much of my research results and perspectives on learning and language over the period 1992-1997 have been compiled in the monograph The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar published by Kluwer Academic Publishers . Here are my other publications sorted by area. Some of them are downloadable.

MACHINE LEARNING AND INFORMATION EXTRACTION

• S. Kutin and P. Niyogi. Almost-everywhere algorithmic stability and generalization error. Technical report TR-2002-03, University of Chicago, 2002. 6 Download
• S. Kutin and P. Niyogi. The interaction of stability and weakness in Adaboost. Technical report TR-2001-30, University of Chicago, 2001.Download
• M. Belkin and P. Niyogi. Semi-supervised learning on Riemannian manifolds. 2002. Submitted to Journal of Machine Learning Research. Download
• M. Belkin and P. Niyogi. Semi-supervised learning on Riemannian manifolds. To appear in Journal of Machine Learning Research. [Postscript]
• M. Belkin and P. Niyogi, "Using manifold structure for partially labelled classification," Advances in NIPS, vol. 15, 2003.
• M. Belkin and P. Niyogi, "Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering" in T. G. Diettrich, S. Becker, and Z. Ghahramani (eds:) Advances in Neural Information Processing Systems 14. MIT Press, Cambridge, MA 2002. Download
• Xiaofei He and Partha Niyogi, "Locality Preserving Projections", Tech Report TR-2002-09 Download
• P. Niyogi and F. Girosi, ``On the Relationship between Generalization Error, Hypothesis Complexity and Sample Complexity in Regulaization Networks,'' Neural Computation, Vol. 8.4, 1996. (Version of MIT AI Memo-1467). Download
• P. Niyogi and F. Girosi, ``Generalization Error Bounds for for Function Approximation from Scattered Noisy Data,'' Advances in Computational Mathematics , Vol. 10, No. 1, 1999. Download
• P. Niyogi, ``Free to Choose: Investigating the Sample Complexity for Active Learning of Real Valued Functions,'' presented at the International Conference on Machine Learning (ICML-95) Lake Tahoe, CA, July, 1995.
• P. Niyogi and F. Girosi, ``Approximation and Estimation Bounds for Radial Basis Function Networks,'' Presented at IMACS World Congress on Computation and Applied Mathematics, Atlanta, Georgia, July 1994.
• K. K. Sung and P. Niyogi, ``An Active Learning Formulation for Function Approximation,'' In Advances in Neural Information Processings Systems 7, San Mateo, CA, 1995. Download
• P. Niyogi and N. K. Karmarkar, ``An Approach to Data Reduction and Clustering with Theoretical Guarantees,'' to appear, Proceedings of International Conference on Machine Learning (ICML-2000), Stanford, CA, July, 2000.
• P. Niyogi,"Perspectives from the Informational Complexity of Learning," to appear, Proceedings of International Conference of Circuits and Systems, Geneva, Switzerland, May, 2000.
• P. Niyogi, J. B. Pierrot, and O. Siohan, "Multiple Classifiers by Constrained Minimization," to appear, Proceedings of International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey, June, 2000.
• P. Niyogi, ``Sequential Optimal Recovery: A Paradigm for Active Learning,'' AI Memo-1514, MIT, March,1995.

• K. K. Sung and P. Niyogi, ``An Active Formulation with Applications to Object Detection,'' submitted to International Journal of Pattern Recognition and AI. (Version of MIT AI Memo-1483).
• P. Niyogi, F. Girosi, and T. Poggio, ``Incorporating Prior Knowledge in Machine Learning by Creating Virtual Examples,'' Proceedings of IEEE, Vol. 86.11, 1998. Download
• P. Niyogi and K. K. Sung,``Epsilon Focusing -- A Strategy for Active Example Selection,'' Knowledge Based Systems Journal, Vol. 10.7, 1998.
• C. Burges, F. Girosi, P. Niyogi, T. Poggio, B. Scholkopt, K. Sung, and V. Vapnik, ``Choosing RBF Centers with the Support Vector Algorithm'', IEEE Transactions in Signal Processing, Vol. 45, No. 11, Nov., 1997. (Version of MIT AI Memo-1599).
• K. K. Sung and P. Niyogi, ``Active Learning the Weights of an RBF Network,'' presented to IEEE--Neural Networks and Signal Processing Conference, September, 1995, Boston. Download
• P. Niyogi and K.K.Sung,``Epsilon Focusing -- A Strategy for Active Example Selection,'' Pacific Asia Conference on Knowledge Discover and Data Mining, Singapore, Feb. 1997.

THE HUMAN LANGUAGE SYSTEM

• P. Niyogi and R. C. Berwick, ``Learning From Triggers,'' Linguistic Inquiry, Vol. 28.1, 1996.
• P. Niyogi and R. C. Berwick, ``A Language Learning Model for Finite Parameter Spaces,'' Cognition , Vol. 61, pp. 161-193, 1996.
• P. Niyogi and R. C. Berwick, ``Formal Models for Learning Finite Parameter Spaces,'' Presented at the Workshop on Cognitive Models for Language Acquisition, April 1994, Tilburg University, The Netherlands. (to appear also as book chapter of Models of Language Learning: Inductive and Deductive Approaches ed: Peter Broeder and Jaap Murre, Oxford University Press).
• P. Niyogi and R. C. Berwick, ``A Markov Language Learning Model for Finite Parameter Spaces,'' presented at the Conference of the Association for Computational Linguistics, New Mexico, July 1994.
• P. Niyogi and R. C. Berwick, ``Formalizing Triggers: A Learning Model for Finite Spaces,'' AI Memo-1443, MIT, Nov. 1993.

• Komarova, N. L., Niyogi, P. and Nowak, M. A. (2001) The evolutionary dynamics of grammar acquisition, J. Theor. Biology, 209(1), pp. 43-59. Download
• Martin A. Nowak, Natalia Komarova, and Partha Niyogi. Evolution of universal grammar. Science, 291:114-118, 2001.
• P. Niyogi, ``Models of Cultural Evolution and their Application to Language Change,'' chapter in Language Evolution through Language Acquisition, (E. J. Briscoe, editor), Cambridge University Press, 1999.
• P. Niyogi, ``Modeling the Dynamics of Historical Linguistics,'' New England Conference on Complex Systems, Sept. 1997, Nashua, NH.
• P. Niyogi and R. C. Berwick, ``Evolutionary Consequences of Language Learning,'' Journal of Linguistics and Philosophy, Vol. 17, 1997.
• P. Niyogi and R. C. Berwick, ``A Dynamical Systems Model for Language Change'', Complex Systems, Vol. 11., pp. 161-204, 1997. Download
• P. Niyogi and R. C. Berwick, ``The Logical Problem of Language Change: A Case Study of European Portuguese,'' Syntax: A Journal of Theoretical, Experimental, and Interdisciplinary Research, Vol. 1, 1998.
• P. Niyogi and R. C. Berwick, ``Populations of Learners: The Case of European Portuguese,'' Nineteenth Annual Meeting of the Cognitive Science Society, August, 1997, Stanford, CA.
• P. Niyogi and R. C. Berwick, ``Evolution of Portuguese,'' Sao Paolo, Brazil, 1996
• R. C. Berwick, P. Niyogi, and C. Yang,''Language Evolution and the Minimalist Program: the Origins of Syntax,'' Conference on Human Language Evolution, April, 1996, Edinburgh, U.K.
• P. Niyogi, ``Explaining Language Change: Complex Consequences of Simple Learning Algorithms,'' presented at AAAI Fall symposium on Complex Behaviors, Nov. 9-11, 1996, MIT, Cambridge, MA.
• P. Niyogi and R. C. Berwick, ``Dynamical Systems for Language Change in Parametric Grammars'', presented at the Conference on Mathematics of Language, October, 1995, University of Pennsylvania.
• P. Niyogi, ``Formal Models of Parameter Acquisition and Associated Models of Parameter Change,'' presented at the Workshop on Formal Models of Language Learnability, May 15-17, 1995, University of Maryland.
• P. Niyogi and R. C. Berwick, ``The Logical Problem of Language Change,'' AI Memo-1516, MIT, July, 1995.Download

• Amit, Y., Koloydenko, A. and Niyogi, P., Robust acoustic object detection. (2002), submitted to Journal of Acoustical Society of America Download
• P. Niyogi and P. Ramesh, ``The Voicing Feature for Stop Consonants: Recognition Experiments with Continuously Spoken Alphabets'', to appear, Speech Communication.
• C. Burges, P. Niyogi, S. Chari, and C. Nohl, ``Discriminative Gaussian Mixture Models for Speaker Identification,'' preprint (short version presented at NIPS-Workshop on Large Margin Classifiers, Dec., 1998).
• P. Niyogi and M. M. Sondhi, "Detecting Stop Consonants in Continuous Speech," J. Acoust. Soc. Am. 111, 1063 (2002) Download (JASA subscription required)
• P. Niyogi and P. Ramesh, "Incorporating Voice Onset Time to Improve Letter Recognition Accuracies," in IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Seattle, WA, May 1998, pp. 13 - 16.
• P. Niyogi, C. Burges, P. Ramesh, ``Distinctive Feature Detection using Support Vector Machines,'' Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona, 1999. Download
• P. Niyogi, C. Burges, P. Ramesh, ``Capacity Control in Support Vector Machines and their Application to Feature Detection Problems,'' preprint
• P. Niyogi, E. Petajan, J. Zhong, ``A Feature Based Representation for Audio Visual Speech Recognition,'' Proceedings of the Audio Visual Speech Conference, Santa Cruz, CA, 1999.
• P. Ramesh and P. Niyogi, ``The Voicing Feature for Stop Consonants: Acoustic-Phonetic Analyses and ASR Experiments,'' Proceedings of the International Conference on Spoken Language Processing, Sydney, Australia, Nov. 30-Dec. 4, 1998.
• P. Niyogi, P. Mitra, M. M. Sondhi, ``A Detection Framework for Locating Phonetic Events,'' Proceedings of the International Conference on Spoken Language Processing, Sydney, Australia, Nov. 30-Dec. 4, 1998.
• P. Niyogi, ``Modelling Speaker Variability and Imposing Speaker Constraints in Phonetic Classification,'' LCS Tech-Report-533, MIT, Feb.,1992.
• P. Niyogi and V. W. Zue, ``Correlation Analysis of Vowels and their Application to Speech Recognition,'' presented at EUROSPEECH '91 in Genoa.

• P. Niyogi and G. K. Sinha, ``A PC-Based Tabla Beat recognition system,'' presented at the Indian Conference on Computers and Communications, BARC, September, 1988.
• P. Niyogi ``A PC-Based Tabla Beat Recognition System,'' Bachelor's Thesis submitted to Indian Institute of Technology, New Delhi. (Synopsis accepted for publication in Computer Music Journal, MIT Press.)