Soft computing

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.

Introduction

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

Components of soft computing include:

• Machine learning, including:
  • Neural networks (NN)
    • Perceptron
  • Support Vector Machines (SVM)
• Fuzzy logic (FL)
• Evolutionary computation (EC), including:
  • Evolutionary algorithms
    • Genetic algorithms
    • Differential evolution
  • Metaheuristic and Swarm Intelligence
    • Ant colony optimization
    • Particle swarm optimization
    • Cuckoo Search Algorithm
    • Weed Optimization Algorithm
• Ideas about probability including:
  • Bayesian network

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.

External links

• EUROPEAN CENTRE FOR SOFT COMPUTING
• BISC SIG IN PHILOSOPHY OF SOFT COMPUTING
• SOCO: UPC Group on Soft Computing Systems
• http://www.soft-computing.de/def.html
• https://web.archive.org/web/20160310135547/http://dspace.nitrkl.ac.in:8080/dspace/bitstream/2080/1136/1/subudhi.pdf