Analysis of Symbol Generation and Integration in a Unified Model Based on a Neural Network
Yukari Yamauchi*, and Shun'ichi Tano**
*Division of Natural Science, International Christian University, 3-10-2 Osawa, Mitaka, Tokyo 181-8585, Japan
**Graduate School of Information Systems, University of Electro-Communications, 1-5-1 Chofugaoka, Chofu, Tokyo 182-8585, Japan
The computational (numerical information) and symbolic (knowledge-based) processing used in intelligent processing has advantages and disadvantages. A simple model integrating symbols into a neural network was proposed as a first step toward fusing computational and symbolic processing. To verify the effectiveness of this model, we first analyze the trained neural network and generate symbols manually. Then we discuss generation methods that are able to discover effective symbols during training of the neural network. We evaluated these through simulations of reinforcement learning in simple football games. Results indicate that the integration of symbols into the neural network improved the performance of player agents.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.