written 8.0 years ago by | • modified 3.0 years ago |
Mumbai University > Computer Engineering > Sem 7 > Soft Computing
Marks: 5M
Year: Dec 2015, May 2016
written 8.0 years ago by | • modified 3.0 years ago |
Mumbai University > Computer Engineering > Sem 7 > Soft Computing
Marks: 5M
Year: Dec 2015, May 2016
written 8.0 years ago by |
Soft Computing:
Soft computing is an emerging approach to computing which parallel the remarkable ability of the human mind to reason and learn in a environment of uncertainty and imprecision. Some of it’s principle components includes:Neural Network(NN),Fuzzy Logic(FL)Genetic Algorithm(GA)T.
Neural Network (NN) : for learning and adaptive
Fuzzy set: for knowledge repetitive via fuzzy
Genetic Algorithm: for evaluation computation
These methodologies form the core of soft computing.
Hybridization of thee three creates the successful synergic effect; this is, hybridization creates the situation where different entities cooperate advantageously for a final outcome.
Hard Computing | Soft Computing |
---|---|
Hard computing is conventional computing, requires a precisely stated analytic model and often a lot of computation time. | Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty, partial truth, and approximation. In effect, the role model for soft computing is the human mind. |
Hard computing based on binary logic, crisp systems, numerical analysis and crisp software | Soft computing based on fuzzy logic, neural nets and probabilistic reasoning. |
Hard computing has the characteristics of precision and categoricity. Although in hard computing, imprecision and uncertainty are undesirable properties, | The soft computing, approximation and dispositionality. in soft computing the tolerance for imprecision and uncertainty is exploited to achieve tractability, lower cost, high Machine Intelligence Quotient (MIQ) and economy of communication |
Hard computing requires programs to be written, uses two-valued logic, is deterministic,,requires exact input data, is strictly sequential, produces precise answers | soft computing can evolve its own programs, can use multi valued or fuzzy logic, incorporates stochastic, can deal with ambiguous and noisy data, allows parallel computations,,can yield approximate answers. |