Mixing Binary and Continuous Connection Schemes for Knowledge Access

Abstract

We present BACAS, a Binary and Continuous Activation System which is a parallel process content-addressable memory model. BACAS is designed for the representation and retrieval of 'knowledge of the world' for automatic natural language understanding. In its present form, BACAS is a two-layered system with 10 K-structures (like scripts) in the binary output macro-layer represented by 46 Threshold Knowledge Units and 184 processing elements (like action events) in the continuous activation micro-layer. We discuss the problems of combining two types of connection system and describe a simulation in which the system moves from one pattern to the next in response to external input. A new tool for connection systems, the pulse-out. is introduced. This is a device which replaces the Boltzmann Machine in creating energy leaps. The pulse-out also has the advantage, in the current system, of setting the state of the system a short Hamming distance from an appropriate pattern.