제어로봇시스템학회:학술대회논문집
- 제어로봇시스템학회 2001년도 ICCAS
- /
- Pages.41.5-41
- /
- 2001
Neural Networks which Approximate One-to-Many Mapping
초록
A novel method is introduced for determining the weights of a regularization network which approximates one-to-many mapping. A conventional neural network will converges to the average value when outputs are multiple for one input. The capability of proposed network is demonstrated by an example of learning inverse mapping.
키워드