A trial to represent dynamic concepts

2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622) Pub Date : 2002-08-07 DOI:10.1109/NAFIPS.2002.1018112

K. Kawase, T. Takagi

引用次数: 0

Abstract

We consider the expression and recognition of dynamic concepts by regarding the movement patterns learned in a recurrent neural net as symbols. We then develop a method to express more abstract dynamic concepts by combining them with symbols and connecting several recurrent neural networks. Application of the method to actual recognition cases, ball bouncing and dancing, demonstrated its effectiveness. These experiments show the ability of the method to deal with dynamic concepts that are difficult to describe because of vagueness.

查看原文本刊更多论文

表示动态概念的尝试

我们将递归神经网络中学习到的运动模式作为符号来考虑动态概念的表达和识别。然后，我们开发了一种通过将抽象的动态概念与符号结合并连接几个递归神经网络来表达抽象动态概念的方法。将该方法应用于弹跳球和跳舞等实际识别案例，验证了该方法的有效性。这些实验表明，该方法能够处理由于模糊性而难以描述的动态概念。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2002 Annual Meeting of the North American Fuzzy Information Processing Society Proceedings. NAFIPS-FLINT 2002 (Cat. No. 02TH8622)

自引率

0.00%

发文量