We investigate the behavioral patterns of a population of agents, each cont
rolled by a simple biologically motivated neural network model, when they a
re set in competition against each other in the minority model of Challet a
nd Zhang. We explore the effects of changing agent characteristics, demonst
rating that crowding behavior takes place among agents of similar memory, a
nd show how this allows unique "rogue" agents with higher memory values to
take advantage of a majority population. We also show that agents' analytic
capability is largely determined by the size of the intermediary layer of
neurons. In the context of these results, we discuss the general nature of
natural and artificial intelligence systems, and Suggest intelligence only
exists in the context of the surrounding environment (embodiment).