With increasing sources of data, there is a quest of finding meaning from it and utilizing it for better decision making and deriving autonomous actions. However, as the number of dimensions and input variables increase, the search through the solution space becomes computationally intensive and application of simply the brute force and distributed computing is not sufficient. We can leverage SI algorithms in order to tag the important dimensions with higher weights impacting the overall outcome. In this particular scenario, the velocity of the data generation adds a level of complexity due to the variation in the data that is received.
Some of the challenges that need to be solved when designing the swarm of artificial agents are related to the dynamic target space, the state of the environment changes very rapidly (even after an optimization is performed and the pheromone level is decided by the intelligent agent). Once the swarm finds global optima, the actual value...