Learning complex combinations of operations in a hybrid architecture

Abstract

The reasons why machine learning appears limited to relatively simple control problems are analyzed. A primary issue is that any condition detected by a learning system acquires multiple behavioural meanings. As learning continues, the need to preserve these meanings severely constrains the architectural form of the system. A hybrid architecture called the recommendation architecture in which the preservation of such meanings is explicitly managed is compared with a wide range of alternative learning approaches. It is concluded that systems with this recommendation architecture have the capability to learn to solve complex control problems.