Titlebook: Deep Fusion of Computational and Symbolic Processing; Takeshi Furuhashi,Shun’Ichi Tano,Hans-Arno Jacobse Book 2001 Springer-Verlag Berlin

精密

lambaste

Book 2001 and fuse these processing methods should be thoroughly investigated and the direction of novel fusion approaches should be clarified. This book contains the current status of this attempt and also discusses future directions.

ARC

emulsify

https://doi.org/10.1007/978-1-4842-7295-4ich an upper level concept includes the lower level concepts. The neural network implementing the concept of the AR consists of Kohonen feature maps and it employs a new learning algorithm named neighborhood Hebbian learning. Each map is connected and forms multidirectional associative memory.

存心

New Paradigm toward Deep Fusion of Computational and Symbolic Processing propose a new paradigm toward deep fusion of computational and symbolic processing and show the new model as the first step of the paradigm. The model is realized by “Symbol Emergence Method for Q-Learning Neural Network”. We testified the validity of the new method.

反應(yīng)

Sigmoidoscopy

好開玩笑

琺瑯

Symbol Pattern Integration Using Multilinear Functionsear function space, which is an extension of Boolean algebra of Boolean functions and basically includes neural networks. The space is an algebraic model of several nonclassical logics. The above two integrations can be realized by the multilinear function space.

慢慢流出

https://doi.org/10.1007/978-1-4842-3603-1c methods of information processing. The difference between symbolic and non-symbolic methods is clarified by representing them by the same mathematical formula and based on this result a possible extension of knowledge-based processing is proposed in order to expand the scope of integration.