A PROLOG-LIKE INFERENCE SYSTEM BASED ON NEURAL LOGIC - AN ATTEMPT TOWARDS FUZZY NEURAL LOGIC PROGRAMMING

Research under the name of Neural Logic Networks is an attempt to inte grate connectionist models and logic reasoning [8, 9]. With a Neural L ogic Network, a simple neural network structure with suitable weight(s ) can be used to represent a set of flexible operations, which offer i ncreased possibilities in dealing with inference in real-world problem solving. They also possess useful properties in an extended logic sys tem which is called Neural Logic. One of the important features of Neu ral Logic is that all its operations can be defined and realized by ne ural networks, which form Neural Logic Networks. As one part of the re search on Neural Logic Networks, fuzzy neural logic programming has be en proposed [6]. This paper introduces a Prolog-like inference system based on Neural Logic as an implementation of fuzzy neural logic progr amming. In this system, fuzzy reasoning is executed by the Neural Logi c inference engine with incomplete or uncertain knowledge. The framewo rk of the system and its inference mechanism are described.