This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages)(Learn how and when to remove this template message)
Soft computing, as opposed to traditional computing, deals with approximate models and gives solutions to complex real-life problems. Unlike hard computing, soft computing is tolerant of imprecision, uncertainty, partial truth, and approximations. In effect, the role model for soft computing is the human mind. It was conceived by Lotfi Zadeh, pioneer of a mathematical concept known as fuzzy sets which led to many new fields such as fuzzy control systems, fuzzy graph theory, fuzzy systems, and so on. Zadeh observed that people are good at 'soft' thinking while computers typically are 'hard' thinking. People use concepts like 'some', 'most', or 'very' rather than 'hard' or precise concepts of 3.5 or 102. People want a 'warm' glass of milk, not one that is 102 degrees. In general, people are good at learning, finding patterns, adapting and are rather unpredictable. In 'hard' computing, by contrast, machines need precision, determinism and measures, and although pattern recognition happens, there is a 'brittleness' if things change - it cannot easily adapt. 'Soft' computing by contrast embraces chaotic, neural models of computing that are more pliable. Because there is no known single method that lets us compute like people, soft computing involves using a combination of methods that each bring something helpful to achieve this goal. The principal constituents of Soft Computing (SC) are Fuzzy Logic (FL), Evolutionary Computation (EC), Machine Learning (ML) and Probabilistic Reasoning (PR), with the latter subsuming belief networks and parts of learning theory.
Soft Computing became a formal area of study in Computer Science in the early 1990s. Earlier computational approaches could model and precisely analyze only relatively simple systems. More complex systems arising in biology, medicine, the humanities, management sciences, and similar fields often remained intractable to conventional mathematical and analytical methods. However, it should be pointed out that complexity of systems is relative and that many conventional mathematical models have been very productive in spite of their complexity.
Soft computing deals with imprecision, uncertainty, partial truth, and approximation to achieve computability, robustness and low solution cost. As such it forms the basis of a considerable amount of machine learning techniques. Recent trends tend to involve evolutionary and swarm intelligence based algorithms and bio-inspired computation.
Components of soft computing include:
- Machine learning, including:
- Fuzzy logic (FL)
- Evolutionary computation (EC), including:
- Ideas about probability including:
Generally speaking, soft computing techniques resemble biological processes more closely than traditional techniques, which are largely based on formal logical systems, such as sentential logic and predicate logic, or rely heavily on computer-aided numerical analysis (as in finite element analysis). Soft computing techniques are intended to complement each other.
Unlike hard computing schemes, which strive for exactness and full truth, soft computing techniques exploit the given tolerance of imprecision, partial truth, and uncertainty for a particular problem. Another common contrast comes from the observation that inductive reasoning plays a larger role in soft computing than in hard computing.
- Zadeh, Lotfi A., "Fuzzy Logic, Neural Networks, and Soft Computing," Communications of the ACM, March 1994, Vol. 37 No. 3, pages 77-84.
- X. S. Yang, Z. H. Cui, R. Xiao, A. Gandomi, M. Karamanoglu, Swarm Intelligence and Bio-Inspired Computation: Theory and Applications, Elsevier, (2013).
- D. K. Chaturvedi, "Soft Computing: Techniques and Its Applications in Electrical Engineering", Springer, (2008).