Understanding human motions can be posed as a pattern recognition problem. In order to convey visual messages to a receiver, a human expresses motion patterns. Loosely called gestures, these patterns are variable but distinct and have an associated meaning. The Pattern recognition by any computer or machine can be implemented via various methods such as Hidden Harkov Models, Linear Programming and Neural Networks. Each method has its own advantages and disadvantages, which will be studied separately later on. This paper reviews why using ANNs in particular is better suited for analyzing human motions patterns.