ABSTRACT
Fuzzy logic, artificial neural networks, and evolutionary algorithms are a few examples of soft computing techniques. Soft computing systems can analyze erroneous and uncertain input and generate trustworthy conclusions by utilizing fuzzy logic, neural networks, and genetic algorithms (GA). In order to address complex issues, soft computing techniques employ a variety of bio-inspired strategies, including neural networks, GAs, and swarm intelligence. A prominent soft computing method is fuzzy logic, which is founded on the idea of using fuzzy sets and fuzzy rules to describe uncertain or inaccurate information. Although the authors have highlighted the holistic and general demerits and limitations of soft computing, the drawbacks are more unique to the method than general because of their diverse frameworks. Moreover, this chapter demonstrated the deficiency of hard computing techniques in handling some complex real-life problems delineated by noise, and uncertainties thus failing in mimicking intelligent human-like decision makings.
