Title:    Theory & Neural Architecture   (Lecture)

Time: Wednesday, March 17, 3:45 PM - 5:45 PM

Location:    Tucson 4

Chair: David Miller    (Pennsylvania State University)

3:45 PM    NNSP-2.1
Global Asymptotic Convergence of Nonlinear Relaxation Equations Realised Through a Recurrent Perceptron
Danilo P Mandic (Signal Processing Section, Department of Electrical Engineering, Imperial College, London), Jonathon A Chambers (Signal Processing Section, Department of Electrical Engineering, Imperial College, London, UK)
[abstract]  [manuscript]

4:00 PM NNSP-2.2
A Neural Network for Data Association
Michel Winter, Gérard Favier (Laboratoire I3S)
[abstract]  [manuscript]

4:15 PM NNSP-2.3
Training MLPs Layer-by-layer with the Information Potential
Dongxin Xu, Jose C. Principe (Computational NeuroEngineering Laboratory, Department of Electrical and Computer Engineering, University of Florida)
[abstract]  [manuscript]

4:30 PM NNSP-2.4
Time Series Prediction via Neural Network Inversion
Lian Yan, David J Miller (The Pennsylvania State University)
[abstract]  [manuscript]

4:45 PM NNSP-2.5
Partial Likelihood for Estimation of Multi-Class Posterior Probabilities
Tulay Adali, Hongmei Ni, Bo Wang (University of Maryland, Baltimore County)
[abstract]  [manuscript]

5:00 PM NNSP-2.6
Hybrid Sequential Monte Carlo / Kalman Methods to Train Neural Networks in Non-Stationary Environments
Joao F de Freitas, Mahesan Niranjan, Andrew H Gee (Cambridge University)
[abstract]  [manuscript]

5:15 PM NNSP-2.7
RECONSTRUCTION AND PREDICTION OF NONLINEAR DYNAMICAL SYSTEMS : A HIERARCHICAL BAYES APPROACH WITH NEURAL NETS
Takashi Matsumoto, Motoki Saito, Yoshinori Nakajima, Junjiro Sugi, Hiroaki Hamagishi (Waseda University)
[abstract]  [manuscript]

5:30 PM NNSP-2.8
Sequential Bayesian Computation of Logistic Regression Models
Mahesan Niranjan (Cambridge University)
[abstract]  [manuscript]

< NNSP-1 NNSP-3 >

Last Update: February 4, 1999 Ingo Höntsch