전자공학회논문지B (Journal of the Korean Institute of Telematics and Electronics B)
- 제32B권3호
- /
- Pages.503-511
- /
- 1995
- /
- 1016-135X(pISSN)
신경회로망에서 일괄 학습
Batch-mode Learning in Neural Networks
초록
A batch-mode algorithm is proposed to increase the speed of learning in the error backpropagation algorithm with variable learning rate and variable momentum parameters in classification problems. The objective function is normalized with respect to the number of patterns and output nodes. Also the gradient of the objective function is normalized in updating the connection weights to increase the effect of its backpropagated error. The learning rate and momentum parameters are determined from a function of the gradient norm and the number of weights. The learning rate depends on the square rott of the gradient norm while the momentum parameters depend on the gradient norm. In the two typical classification problems, simulation results demonstrate the effectiveness of the proposed algorithm.
키워드