한국지능시스템학회:학술대회논문집 (Proceedings of the Korean Institute of Intelligent Systems Conference)
- 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
- /
- Pages.113-117
- /
- 1998
Self-Relaxation for Multilayer Perceptron
- Liou, Cheng-Yuan (Dept. of Computer Information Engineering, National Taiwan University) ;
- Chen, Hwann-Txong (Dept. of Computer Information Engineering, National Taiwan University)
- 발행 : 1998.06.01
초록
We propose a way to show the inherent learning complexity for the multilayer perceptron. We display the solution space and the error surfaces on the input space of a single neuron with two inputs. The evolution of its weights will follow one of the two error surfaces. We observe that when we use the back-propagation(BP) learning algorithm (1), the wight cam not jump to the lower error surface due to the implicit continuity constraint on the changes of weight. The self-relaxation approach is to explicity find out the best combination of all neurons' two error surfaces. The time complexity of training a multilayer perceptron by self-relaxationis exponential to the number of neurons.