The Study of the Learning Ability of Multi-layer Neural Networks

• Main Authors: Yu,Wen-Jen, 于文貞
• Other Authors: Liou,Cheng-Yuan
• Format: Others
• Language: zh-TW
• Published: 1994
• Online Access: http://ndltd.ncl.edu.tw/handle/62408512533758493389

碩士 === 國立臺灣大學 === 資訊工程研究所 === 82 === The objective of this research is to propose methods on solving the learning problems of multi-layer neural networks. The most well-known and commonly used learning algorithm is Back Propagation (BP) algorithm. There are three main drawbacks of BP: 1. the slowness of the learning speed, 2. the convergence to local minima, and 3. the absence of any theoretical result, allowing for a priori determination of an optimal network architecture for a given task. To solve these problems, we propose three methods: The first is to initialize weights in multi-layer quadratic sigmoid networks; The second is to learn in successive residual space; The third is using the topology preserving maps formmed in MLPs. These methods can be applied to pattern recognition problems espically when the training patterns have lined structure.