Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)
- 1989.07a
- /
- Pages.495-499
- /
- 1989
A Neural Network for Concept Learning : Recognitron
개념 학습에 의한 신경 회로망 컴퓨터
- Lee, Ki-Han (Seoul Nat'l Univ. Dept. of Comp. Eng.) ;
- Whang, Hee-Yoong (Seoul Nat'l Univ. Dept. of Comp. Eng.) ;
- Kim, Choon-Suk (Soong Sil Univ Dept. of Elec. Eng.)
- Published : 1989.07.21
Abstract
Concept is the set of selected neurons in a stable state of a neurel network. The Recognitron uses a parallel feedback structure to support concept learning. A number of clusters can exist in response to a given input, each of which make up a selective neuron. There are supervised and unsupervised learnig methods in concept teaming. In this paper, we have chosen unsupervised learning. Also, a new concept called relaxational learning has been introduced to stop runaway weights
Keywords