For continuous use intelligent systems needs the support of machine learning experts, what is expensive. To reduce costs it is reasonable to implement long life learning intelligent systems. Idea of this type of systems consists in continuous adaptation of system for new conditions of execution. This allows to stay independent from machine learning expert intervention, but allows to invite human domain experts. Nowadays, acceleration of development of life long learning systems poses the question of the evaluation of this type of systems.

In our article we propose the evaluation methodology of lifelong learning systems. It contains both a evaluation of human-assisted learning(active, interactive learning) out of context of lifelong learning and evaluation of systems across time, and in this context described idea of evaluation of life long learning intelligent systems.