상세정보
학술대회
Flexible Reasoning of Boolean Constraints in Recurrent Neural Networks with Dual Representation
- 저자
- 장원일, 송현아, 이수영
- 발행일
- 201311
- 출처
- International Conference on Neural Information Processing (ICONIP) 2013 (LNCS 8226), v.8226, pp.106-112
- 협약과제
- 13PR4300, 영상객체 인식기반 지식융합 서비스 플랫폼 개발, 조기성
- 초록
- In this paper, we propose a recurrent neural network that can flexibly make inferences to satisfy given Boolean constraints. In our proposed network, each Boolean variable is represented in dual representation by a pair of neurons, which can handle four states of true, false, unknown, and contradiction. We successfully import Blake's classical Boolean reasoning algorithm to recurrent neural network with hidden neurons of Boolean product terms. For symmetric Boolean functions, we designed an extended model of Boolean reasoning which can drastically reduce the hardware cost. Since our network has only excitatory connections, it does not suffer from oscillation and we can freely combine multiple Boolean constraints. © Springer-Verlag 2013.
- KSP 제안 키워드
- Boolean constraints, Boolean reasoning, Dual representation, Extended model, Hidden Neurons, Product Terms, Reasoning algorithm, Recurrent Neural Network(RNN), Symmetric boolean functions, hardware cost