Fish School Search

Real world problems are packed with complex issues often hard to be computed. Searching for parameters or candidate solutions is frequently associated with these complexities. The reason for that is chiefly related to the large dimensionalities of some search spaces. In general, problems involving large search spaces use traditional computer intensive methods that are, quite often, expensive (i.e. resource consuming). Nature-inspired algorithms, on the other hand, are able to deal reasonably well with the abovementioned difficulties. In this chapter, we provide an overview of a novel approach for searching in high-dimensional spaces based on the behaviors of fish schools. As any other intelligent technique based on population, Fish School Search (FSS) greatly benefits from the collective emerging behavior that increases mutual survivability. Broadly speaking, FSS is composed of operators that can be grouped in the following categories: feeding, swimming and breeding. Together, these operators provide computing behavior such as: (i) high-dimensional search ability, (ii) automatic selection between exploration and exploitation, and (iii) self-adaptable guidance towards sought solutions. This chapter seeks to explain the main ideas behind FSS to researchers and practitioners. In addition, we include examples and simulations aimed at clarifying the simplicity and potentials of FSS.