오류 역전파(Error Backpropagation) 학습 알고리즘을 이용한 숫자 인식에 관한 연구 = A Study on Number Recognition Using Error Backpropagation Learning Algorithm

다국어 초록 (Multilingual Abstract)

This paper proposes and implements a multilayered neural network system which can learn and recognize the bitmap number images. To learn the bimap number, the system uses the learning algorithm, that is "Error Backpropagation Learning Algorithm" which is based on the delta rule. For the design of the system, we must consider not only the structure of the neural network, but also the initial weight value, learning rate and bias. According to the design concept, the system is implemented and then tested with the various number formats. The system can recognize test patterns 100% which are input patterns in learning phase. But with the other format, the system has the 60∼70% recognition.

목차 (Table of Contents)

• 목차
• Abstract = 203
• Ⅰ. 서론 = 203
• Ⅱ. 연구의 배경
• 1. 일반화된 델타 규칙 = 204
• 2. 오류 역전파 학습 알고리즘 = 205
• Ⅲ. 다층 신경망 설계 = 206
• 1. 신경망 설계 고려사항 = 206
• 2. 학습 및 인식 순서 설정 = 206
• 3. 신경망 구조 설계 = 207
• Ⅳ. 다층 신경망 구현 = 207
• Ⅴ. 결론 = 209
• 참고문헌 = 210