Artificial General Intelligence Begins with Recognition: Evaluating the Flexibility of Recognition

Many types of supervised recognition algorithms have been developed over the past halfcentury. However, it remains difficult to compare their flexibility and ability to reason. Part of the difficulty is the need of a good definition of flexibility. This chapter is dedicated to defining and evaluating flexibility in recognition. Artificial Intelligence and even more so Artificial General Intelligence are inseparable from the context of recognition. Recognition is an essential foundation on top of which virtually every function of intelligence is based e.g.: memory, logic, internal understanding, and reasoning. Many logic and reasoning questions can be directly answered by reasoning based on recognition information. Thus it is important to understand forms of flexible recognition structures in order to know how to store and reason based on flexible information. The first section describes various methods that perform recognition. The second section proposes tests and metrics to evaluate flexibility, and the third provides an example of applying the tests to these methods.