Application and evaluation of fusion of symbolic and computational processing

It is indispensable to combine symbolic and computational processing in order to realize a software architecture for next generation intelligent systems. Work has been done on the combination of symbolic and computational processing. However the level of the fusion is not deep, high or wide enough. Firstly our previous works, Model-A and Model-B, are briefly reviewed. The lower layer is a neural network in which Q-learning is simulated. The inputs are the state variables, and the outputs are the Q-values for each action. It is tuned to update and store the 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 the learning. Model-B is extended so as to learn more complex concepts quickly. Secondly they are evaluated from two points of view, the efficiency of the algorithm and the level of the combination of symbolic and computational processing. Then we propose three promising approaches in order to fuse two processing models