Deep fusion of computational and symbolic intelligent processing by symbol emergence

摘要

Through the development of the intelligent user interface system called THE RVI-desk, we found that it was indispensable to combine symbolic and computational processing in order to realize a software architecture for the next-generation intelligent user interface. Several early works toward the combination of symbolic and computational processing were briefly reviewed but the level of fusion is not deep, high and wide enough. Then two simple models, Model-A and Model-B, are described as the first step toward fusing computational and symbolic processing. Model-B is an extension of Model-A. Each of them consists of two layers. The lower layer is a neural network in which Q-learning is simulated. The inputs are state variables, and the outputs are Q-values for each action. It is tuned to update and store Q-table. The upper layer watches the activity in the lower layer to identify the group of nodes that are activated when some action in the lower layer obtains a high reward from the environment. In this way, new symbols emerge that are embedded in the lower layer to speed up learning. Model-B is extended to learn more complex concepts quickly. When an important concept is learned, the corresponding symbol is generalized and embedded in a different place at a lower level. Simulation demonstrated that symbol emergence and the forced application of these symbols in Q-learning greatly improves the performance of players playing a simple football game. This approach is a first step toward "deep fusion of computational and symbolic processing".