改进的SOFM网络算法在语音认知模拟研究中的应用
Application of An Improved SOFM Algorithm In The Simulating Research of Phonological Cognition
针对传统自组织网络存在无效神经元,重复“获胜”等问题,本文提出一种基于距离频率计数器的改进算法,并将其应用于双层网络模型中,实现对汉字语音认知过程的模拟研究。实验结果表明改进的算法能够很好的对汉字和语音进行聚类,改善了网络训练效果。
In this paper, an improved algorithm is presented to solve the problem in the Self-Organizing Neural Network, as some cells would never “win” in the self-organizing process and some others would win again and again. With the improved algorithm, a two-layer SOFM Model is applied in the simulating research of the phonological cognition. The improved algorithm proved good, for the characters and the phonemes was clustered well and the training effects were observed improved.
这个怎么翻译比较好 |
|