Neural network training by integration of adjoint systems of equ

Details Neural network training by integration of adjoint systems of equ Neural network training by integration of adjoint systems of equ

1992-10-27

1999-07-27

Hafiz, Tariq R.

Data processing: artificial intelligence

Neural network

Learning method

706 16, G06F 1518

Patent

active

059307811

ABSTRACT:
A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically, it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved, but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. The trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

REFERENCES:
patent: 4804250 (1989-02-01), Johnson
patent: 4912652 (1990-03-01), Wood
patent: 4918618 (1990-04-01), Tomlinson
patent: 4926064 (1990-05-01), Tapang
patent: 4951239 (1990-08-01), Andes et al.
patent: 4953099 (1990-08-01), Jourjine
patent: 4967369 (1990-10-01), Jourjine
patent: 4990838 (1991-02-01), Kawato et al.
patent: 5046019 (1991-09-01), Basehore
patent: 5046020 (1991-09-01), Filkin
patent: 5050095 (1991-09-01), Samad
patent: 5052043 (1991-09-01), Gaborski
patent: 5058034 (1991-10-01), Murphy et al.
patent: 5075868 (1991-12-01), Andes et al.
patent: 5086479 (1992-02-01), Takenaga et al.
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5105468 (1992-04-01), Guyon et al.
patent: 5276770 (1994-01-01), Castelaz
patent: 5283855 (1994-02-01), Motomura et al.

Affiliated with

Also associated with

Rating

Neural network training by integration of adjoint systems of equ does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network training by integration of adjoint systems of equ, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network training by integration of adjoint systems of equ will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-892847