反馈集成网络的动力学分析及其应用
Dynamic Analysis of Integrated Neural Network with Feedback and its Application
-
摘要: 如何由样本的特征描述得到相应的类别属性,是模式识别的主要研究内容.由控制 论的观点,它是一个黑箱层次.受控制系统启发,文中提出了反馈集成网络模型,使模式识别 系统成为闭环结构,并详细讨论了它的动力学性质,给出系统绝对稳定的充分条件以及相应 的学习算法.在自由手写数字样本库上的实验表明,所提模型与普通前向型神经网络相比,具 有较好的判别性能.Abstract: In pattern recognition, it is important to find a suitable way to decide a sample's class attribute according to its feature description. From the cybernetics point of view, the transformation is a black box. In this paper, we propose a new model integrated neural network with feedback, which can be implemented as a combine model for pattern recognition and is a closed-loop structure. We present the mathematical theorems for its absolute stability and the corresponding learning algorithm. Experiments on totally unconstrained handwritten numeral recognition have confirmed the proposed model's superiority.
-
Key words:
- Metasynthesis /
- supervised learning /
- dynamic system
计量
- 文章访问数: 2677
- HTML全文浏览量: 133
- PDF下载量: 967
- 被引次数: 0