Abstract
A local extended Kalman filter training and pruning approach is proposed to train feedforward networks with the goal of reducing the computational complexity and storage requirement in large-scale practical problems. The performance of the proposed algorithm is demonstrated for the problem of handwritten digit recognition.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Paper version not known
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
