A conceptual foundation for autonomous learning in unforeseen situations

A cognitive agent should have the capability to learn autonomously in completely unforeseen situations. “Unforeseen” means something that was not taken into account in an internal representation of the world. However, it is detectable in the form of anomalous sensor measurements. Two problems must be solved: 1) the “newness” of the situation must be detected, i.e. it should not be allocated (wrongly) to an existing category; and 2) new concepts must be learned so that when a similar situation occurs again it is no longer anomalous. A conceptual framework is presented here based on a form of symbol grounding which emphasises a continual distinction between model-driven expectancy and actual reality. Large differences between expectation and reality indicate that a new concept is required which corresponds more accurately to the sensor data. This results in the autonomous growth and change of symbol groundings. Genetic programming is considered as a tool (both on the symbolic and the subsymbolic levels)