Neural_Network_Training_NLT

Neural_Network_Training_NLT - Neural Network Training...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
LINEAR LEAST SQUARES METHOD Nathan Toner Neural Network Training
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Outline y Brief overview of the method y 2-dimensional falling object dynamics y Network setup y Simulation results y Conclusions
Background image of page 2
Method y Train radial basis function network (RBFN) using linear least-squares technique. y A continuous system can be approximated by a network of Gaussian basis functions as in (1). y The system can be transformed to form (2) as seen in lecture. y The iterative training method becomes (3). Elanayar, Sunil V. T. and Yung C. Shin. “Radial Basis Function Neural Network for Approximation and Estimation of Nonlinear Stochastic Dynamic Systems.” IEEE Transactions on Neural Networks, vol. 5, no. 4 (1994): 594-603. (1) (2) (3)
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2D Falling Object Dynamics y Object falling in 2 dimensions y 5 states: position and velocity in two directions, unknown aerodynamic coefficient y 2 measurements: distance and angle from a radar measurement station located at some position Julier, Simon J. and Jeffrey K. Uhlmann. “A New Extension of the Kalman Filter to Nonlinear Systems.” SPIE vol. 3068 (1997): 182-93.
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/22/2012 for the course ME 697 taught by Professor Staff during the Fall '08 term at Purdue University-West Lafayette.

Page1 / 9

Neural_Network_Training_NLT - Neural Network Training...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online