Journal of the Korean Institute of Telematics and Electronics B (전자공학회논문지B)
- Volume 31B Issue 7
- /
- Pages.179-189
- /
- 1994
- /
- 1016-135X(pISSN)
Time-Varying Two-Phase Optimization and its Application to neural Network Learning
시변 2상 최적화 및 이의 신경회로망 학습에의 응용
- Myeong, Hyeon (Dept. of Elec. Eng., Korea Advanced Institute of Science and Technology(KAIST)) ;
- Kim, Jong-Hwan (Dept. of Elec. Eng., Korea Advanced Institute of Science and Technology(KAIST))
- Published : 1994.07.01
Abstract
A two-phase neural network finds exact feasible solutions for a constrained optimization programming problem. The time-varying programming neural network is a modified steepest-gradient algorithm which solves time-varying optimization problems. In this paper, we propose a time-varying two-phase optimization neural network which incorporates the merits of the two-phase neural network and the time-varying neural network. The proposed algorithm is applied to system identification and function approximation using a multi-layer perceptron. Particularly training of a multi-layer perceptrion is regarded as a time-varying optimization problem. Our algorithm can also be applied to the case where the weights are constrained. Simulation results prove the proposed algorithm is efficient for solving various optimization problems.
Keywords