This document discusses the application of soft computing techniques in electrical engineering. It begins with an introduction to soft computing and its key elements including fuzzy logic, neural networks, evolutionary computation, machine learning and probabilistic reasoning. It then discusses hard computing versus soft computing, defining hard computing as requiring precise analytical models and definitions, while soft computing can handle imprecision. The document outlines several soft computing techniques - neural networks, fuzzy logic, and their applications in power system economic load dispatch and generation level determination to solve complex, non-linear optimization problems in electrical engineering. In conclusion, soft computing provides alternatives to traditional techniques for electrical engineering problems involving uncertainty.