Learning procedure for multi-level neural network

Details Learning procedure for multi-level neural network Learning procedure for multi-level neural network

1997-08-05

1999-02-09

Hafiz, Tariq R.

Data processing: artificial intelligence

Neural network

Learning method

706 16, G06F 1518

Patent

active

058707280

ABSTRACT:
A reiterative learning procedure with training and test processes for a binary supervised neural network includes at least an error signal generator for weighting factor updating in the training process, which generates an error signal that is perturbed in polarity and amplitude in the difference derived by subtracting an output unit signal from corresponding binary teacher signal and then generates the difference as an error signal after a maximum absolute value of differences among erroneous binary output signals has become smaller than a threshold once. A training signal memory stores a set of training signals and adds test signals providing erroneous binary output signals that are transferred from a test signal memory in the test process to the set of training input signals as incremental training input signals. An affordable signal memory stores input signals with sufficiently large margins providing correct binary output signals that are transferred from the training signal memory in the training process and the test signal memory in the test process. The reiterative learning procedure, with minimum necessary training and test input signals and control of the error perturbation in the training process, can provide a binary space to obtain a desired binary output, and also realizes an extremely high generalization ability.

REFERENCES:
patent: 5075868 (1991-12-01), Andes et al.
patent: 5103496 (1992-04-01), Andes et al.
patent: 5129038 (1992-07-01), Kohda et al.
patent: 5640494 (1997-06-01), Jabri et al.
Sang-Hoon Oh et al., Sensitivity analysis of single hidden-layer neural networks with threshold functions, IEEE transactions on neural network, vol. 6, No. 4., pp. 1005-1007, Jul. 1995.
Sang-Hoon Oh et al., Sensitivity of trained neural networks with threshold functions, IEEE Conference on neural networks, pp. 986-991., Jul. 2, 1994.
Szu et al., Control of chaos using neural networks, IJCNN-93, pp. 1781-1784 vol. 2., Oct. 1993.
Yatsuzuka, An error perturbation for learning and detection of local minima in binary 3-layered neural networks, 1995 IEEE Intl. Conference on Neural Network, pp. 63-68., Dec. 1, 1995.

Affiliated with

Also associated with

Rating

Learning procedure for multi-level neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Learning procedure for multi-level neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning procedure for multi-level neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1959932