|
|||||||
|
|
|
|||||
|
|
|||||||
TROLLHETTA AS
contributes with experience
Soft Computing (SC) are Fuzzy Logic (FL), Neural Network (NN) and Evolutionary Computation (EC).
Soft computing differs from conventional (hard) computing in that, unlike hard computing, it is tolerant of imprecision, uncertainty and partial truth. In effect, the role model for soft computing is the human mind. The guiding principle of soft computing is to exploit the tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness and low solution cost.
What is particularly significant is that in both consumer products and industrial systems, the employment of soft computing techniques leads to systems with flexibility and a high degree of Machine Intelligence.
In many cases a problem can be solved most effectively by using Fuzzy Logic, Neural Networks and Evolutionary Computation in combination rather than exclusively. Examples are neurofuzzy systems in consumer and industrial applications.