Nanda Kambhatla

Biography

Nanda Kambhatla was born in Hyderabad, India in 1969. He received the B.Tech degree with first class honors in 1990 in Computer Science and Engineering from the Institute of Technology, Benaras Hindu University, India, and the Ph.D degree in Computer Science and Engineering from the Oregon Graduate Institute of Science & Technology, Oregon, USA, in 1996.

Since 1996, Dr. Kambhatla has worked as a postdoctoral fellow under Prof. Simon Haykin at McMaster University, Canada and as a senior research scientist at WiseWire Corporation, Pittsburgh. He is currently employed as a research staff member at IBM's T.J.Watson Research Center in New York and is working on natural language dialog systems. His research interests include all aspects of machine learning algorithms and their application to textual, speech and image data processing.

Patents

• Nanda Kambhatla, Dimitri Kanevski, Alex Zlatsin, and Wlodek Zadrozny, "Medical Non-Intrusive Prevention based on Network of Embedded Devices" U.S. patent submitted, 1999.
• Nanda Kambhatla, Dimitri Kanevski and Wlodek Zadrozny, "Method and Apparatus for Executing Neural Network Applications on a Network of Embedded Devices", U.S. patent submitted,1999.
• Nanda Kambhatla, Maroun Touma, Catherine Wolf and Wlodek Zadrozny, "System and Method for Accessing Voice Mail from a Remote Server", U.S patent submitted, 1998.
• Wlodek Zadrozny and Nanda Kambhatla, "Method and Apparatus for Creating Speech Recognition Grammars Constrained by Counter-Examples", U.S patent 5,937,385 1999.

Book Chapters

• Nanda Kambhatla and Todd Leen, "Dimension Reduction by Local Principal Component Analysis", Chapter 18, Unsupervised Learning: Foundations of Neural Computation, edited by G. Hinton and T. Sejnowski, a collection of the most significant papers that have appeared in the journal Neural Computation over the last 10 years, The MIT Press, 1999.

Journal Publications

• Nanda Kambhatla, Simon Haykin, and Robert Dony, "Image Compression using a Mixture of Components Model", IEEE Journal of VLSI, 18:3,1998.
• Nanda Kambhatla and Todd Leen, "Dimension Reduction by Local Principal Component Analysis", Neural Computation, 9, pp 1493-1516, 1997.
• Nanda Kambhatla, Simon Haykin, Claude Nahmias, and Robert Dony, "Adaptive Mixture Models for Lossy Image Compression", newsletter of SPIE's international technical working group in electronic imaging, special issue on computational intelligence, 1996.

Conference Publications

• Dragomir Radev, Nanda Kambhatla, Yiming Ye, Catherine Wolf, and Wlodek Zadrozny, "DSML: A Proposal for XML Standards for Messaging Between Components of a Natural Language Dialog System", Proceedings of the Artificial Intelligence and Simulation of Behaviour (AISB) 99 Convention; the workshop on Reference Architectures and Data Standards for Natural Language Processing, 1999.
• Wlodek Zadrozny, Catherine Wolf, Nanda Kambhatla, and Yiming Ye, "Conversation Machines for Transaction Processing", Proceedings of American Association of Artificial Intelligence/ Innovative Applications of Artificial Intelligence, AAAI Press/MIT Press, 1998.
• Nanda Kambhatla, Claude Nahmias, and Simon Haykin, "Compression of Brain MR Images Using an Adaptive Mixture Model, Wavelets, and the Karhunen-Loeve Transform", Radiological Society of North America, 1996.
• Nanda Kambhatla and Todd Leen, "Classifying with Gaussian Mixtures and Clusters", in Tesauro, Touretzky, and Leen, editors, Advances in Neural Information Processing Systems 7, MIT Press, 1995.
• Nanda Kambhatla and Todd Leen, "Fast Non-Linear Dimension Reduction", in Cowan, Tesauro, and Alspector, editors, Advances in Neural Information Processing Systems 6, pp 152-159, Morgan Kaufmann, 1994.
• Nanda Kambhatla and Todd Leen, "Fast Non-Linear Dimension Reduction", in IEEE International Conference on Neural Networks, Vol 3, pp 1213-1218, IEEE, 1993.

Thesis and Talks

• Nanda Kambhatla, "Local Models and Gaussian Mixture Models for Statistical Data Processing", PhD thesis, Dept. of Computer Science & Engg., Oregon Graduate Institute of Science & Technology, Portland, OR, 1996.
• Nanda Kambhatla, "A Local Linear Algorithm for Fast Dimension Reduction", talk in workshop on Algorithms for High Dimensional Data: What Works? And Why?, NIPS workshops, Vail, Colorado, Dec 1994.