Nomen Mum Earl: yet another route to intelligent machine behavior
share
Abstract—A unifying machine learning algorithm is proposed, in which the same processes, data structures and memory manage- ment can be used simultaneously in divergent realms, including conversation, musical composition, and robotics. A central aspect of the project is setting up learning modules that can absorb and use relationships in the input – relationships that are neither analyzed, predicted nor perceived by the programmer. The data, internal objects, and actions available to the program exist as fuzzy points in a quasi-Cartesian, multi-dimensional knowledge space. The geometry of this space is determined by semantic content. Within a combination of this space and a kind of production system we can take advantage of content-addressable memory to replace all search, we can implement table-driven program control, and we can use distributed massively-parallel processing.
READ FULL TEXT