Wan Publications

 

• Dual EKF Methods. Eric A. Wan and Alex T. Nelson. To appear in Kalman Filtering and Neural Networks, 2000. Edited by Simon Haykin, Wiley Publishing. (Gzipped PostScript, 40 pages)

• The Unscented Kalman Filter for Nonlinear Estimation. Eric A. Wan, Rudolph van der Merwe.  To appear in  Symposium 2000 on Adaptive Systems for Signal Processing, Communications, and Control, Oct 2000.(Gzipped PostScript,6 pages)

• Dual Estimation and the Unscented Transformation. Eric A. Wan, Rudolph van der Merwe, and Alex T. Nelson.  In Neural Information Processing Systems, volume 12, Nov 1999. (Gzipped PostScript, 7 pages, 227157 bytes) (PDF, 433649 bytes)

• Noise-Regularized Adaptive Filtering for Speech Enhancement. In Proceedings of EUROSPEECH, Budapest, Hungary, September 1999. (PostScript, 4 pages, 655015 bytes) (PDF, 327629 bytes). Eric Wan and Rudolph van der Merwe.

 
• Networks for Speech Enhancement. E. Wan and A. Nelson, In Handbook of Neural Networks for Speech Processing, Edited by Shigeru Katagiri, Artech House, Boston, USA. 1998, (in press).

 
• A Two-Observation Kalman Framework for Maximum-Likelihood Modeling of Noisy Time Series. A. Nelson and E. Wan. IJCNN'98

 
• Removal of Noise From Speech Using the Dual EKF Algorithm. E. Wan and A. Nelson, ICASSP'98.

 
• Diagrammatic Methods for Deriving and Relating Temporal Neural Network Algorithms. E. Wan and F. Beaufays. E.R. CAIANIELLO SUMMER SCHOOL on Adaptive Processing of Sequences, Vietri sul Mare, Salerno (IT) 6 - 13 September, 1997. Draft Version.

 
• Neural Dual Extended Kalman Filtering: Applications in Speech Enhancement and Monaural Blind Signal Separation. E. Wan and A. Nelson. IEEE Workshop on Neural Networks and Signal Processing. 1997.

 
• Dual Kalman Filtering Methods for Nonlinear Prediction, Smoothing, and Estimation. E. Wan and A. Nelson, Advances in Neural Information Processing Systems: Proceedings of the 1996 Conference, NIPS-9, ed. Mozer,Jordan, and Petsche, 1997.

 
• Combining Fossils and Sunspots: Committee Predictions. E. Wan. ICNN97

 
• Neural Speech Enhancement Using Dual Extended Kalman Filtering. A. Nelson and E. Wan. ICNN97

 
• Adjoint LMS: An Alternative to Filtered-X LMS and Multiple Error LMS. E. Wan. ICASSP96, vol III, pp. 1842-1845

 
• Diagrammatic Derivation of Gradient Algorithms for Neural Networks, E. Wan and F. Beaufays. Neural Computations, 8.1, pp. 182-201 1996.

 
• Speech Enhancement Based on Temporal Processing . H. Hermansky, E. Wan, and Carlos Avendano, ICASSP 1995.

 
• Noise Supression in cellular communications . H Hermansky, E. Wan, and Carlos Avendano. Proc IVTTA 94, pp. 85-88, Kyoto 1994.

 
• Beyond Nyquist: Towards the Recovery of Broad Band Speech from Narrow-Band Speech. C. Avendano, H. Hermansky, and E. Wan. EUROSPEECH 1995.

 
• Relating Real-Time-Backpropagation and Backpropagation-Through-Time: An Application of Flow Graph Interreciprocity. F. Beaufays and E. Wan. Neural Computation, Vol. 6, No. 2, 1994.

 
• Network Reciprocity: A Simple Approach to Derive Gradient Algorithms for Arbitrary Neural Network Structures, E. Wan and F. Beaufays. In Proceedings ICNN'94, San Diego, 1994.

 
• An Efficient First-Order Stochastic Algorithm for Lattice Filters, F. Beaufays and E. Wan. In ICANN'94, Salerno Italy, 1994.

 
• A Unifying View of Some Training Algorithms for Multilayer Perceptrons with FIR Filter Synapses. A. Back, E. Wan, S. Lawrence, and A. Tsoi. IEEE Workshop on Neural Networks and Signal Processing, Sep. 6-8, Ermioni, Greece, 1994

 
• A Unified Approach to Derive Gradient Algorithms for Arbitrary Neural Network Structures, F. Beaufays and E. Wan. In ICANN'94, Salerno Italy, 1994

 
• Time Series Prediction Using a Neural Network with Embedded Tapped Delay-Lines, E. Wan. In Predicting the Future and Understanding the Past, editors. A. Weigend and N. Gershenfeld, SFI Studies in the Science of Complexity, Proc. Vol. XVII, Addison-Wesley, 1993.

 
• Discrete Time Neural Networks . E. Wan. Journal of Applied Intelligence 3, 91-105, 1993.

 
• Modeling Nonlinear Dynamics with Neural Networks: Examples in Time Series Prediction. E. Wan, In Proceedings of the Fifth Workshop on Neural Networks: Academic/Industrial/NASA/Defense, WNN93/FNN93, San Francisco, pages 327-332, November 1993.

 
• Finite Impulse Response Neural Networks with Applications in Time Series Prediction (part a), (part b), (part c), E. Wan. PHD Dissertation, Stanford University, Nov. 1993.

 
• Adaptive Signal Processing. B. Widrow, M. Lehr, F. Beaufays, E. Wan, M. Bilello. In Proceedings of the World Conference on Neural Networks '93, Portland, Oregon, July 12-16, 1993.

 
• Stanford Neural Network Research. B. Widrow, M. Lehr, F. Beaufays, E. Wan, M. Bilello. In 1993 SPIE Proceedings Series, vol. 1965-1966, Orlando, Florida, April 12-16, 1993.

 
• Learning Algorithms for Adaptive Signal Processing and Control. B. Widrow, M. Lehr, F. Beaufays, E. Wan, M. Bilello. In Proceedings of the IEEE International Conference on Neural Networks, volume 1, pages 1-8, San Francisco, CA, March 1993.

 
• Autoregressive Neural Network Prediction: Learning Chaotic Time Series and Attractors. E. Wan, Proceeding of the Summer Workshop on Neural Network Computing for the Electric Power Industry, Stanford, CA, Aug 17-19, 1992.

 
• Using Flow Graph Interreciprocity to Relate Recurrent-Backpropagation and Backpropagation-Through-Time. F. Beaufays and E. Wan. In Proceeding of the Summer Workshop on Neural Network Computing for the Electric Power Industry, Stanford, CA, Aug 17-19, 1992.

 
• Temporal Backpropagation: An Efficient Algorithm for Finite Impulse Response Neural Networks. E. Wan In Proceedings of the 1990 Connectionist Models Summer School, Morgan Kaufmann, pages 131-140.

 
• Neural Network Classification: A Bayesian Interpretation. E. Wan, IEEE Transactions on Neural Networks, Vol. 1, No. 4, pages 303-305, December 1990.

 
• Temporal Backpropagation for FIR Neural Networks. E. Wan, In Proceedings of the International Joint Conference on Neural Networks, San Diego, June 1990.

 
• Development of Neural Network Interface for Direct Control of Neuroprostheses. E. Wan, G. Kovacs, J. Rosen and B. Widrow. In Proceedings of the International Joint Conference on Neural Networks, Washington, DC, Vol 2, pages 3-21, January 1990.

 
• Neural Tree Structured Vector Quantization. E. Wan, P. Ning and B. Widrow. In Proceedings of the International Joint Conference on Neural Networks, Washington, DC, January 1990.

 
• MRIII: A robust algorithm for training analog neural networks. D. Andes, B. Widrow, M. Lehr and E. Wan. In Proceedings of the International Joint Conference on Neural Networks, volume I, pages 533-536, Washington, DC, January 1990.

 

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

 

http://www.ece.ogi.edu/~ericwan         ericwan@ece.ogi.edu