perception being solution

Those systems typically stores their perceptions, their experiences in a knowledge base, so as to use it in later reasoning.

In Georgeon, Olivier L. :: IDEAL MOOC, an approach of recognizing regularities of interactions in past experience and use that regularity to reason of a best action to perform is discussed.

In NARS, observations are stored in database and queried with its Non-Axiomatic Logic when reasoning for an action to be done to achieve a goal.

Those systems typically try to not store observations, instead create a model of all observations, often in terms of adjustable parameters of a function.

Neural Networks, for one, process inputs(observations), and store the model of the observation in it’s weights.

Evolution Algorithm, too, process inputs(trials) with a pool of chromosomes, whose size does not grow, and whose content only change after generations of trials being performed.