Basics of Soft Computing

Basics of Soft Computing

• 1.
  Soft Computing
• 2.
  What is SoftComputing ?  “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”.  Soft Computing is the fusion of methodologies designed to model and enable solutions to real world problems, which are not modeled or too difficult to model mathematically.  The aim of Soft Computing is to exploit the tolerance for imprecision, uncertainty, approximate reasoning, and partial truth in order
• 3.
   Soft Computingis a term used in computer science to refer to problems in whose solutions are unpredictable, uncertain and between 0 and 1.  Soft computing deals with imprecision, uncertainty, partial truth, and approximation to achieve practicability, robustness and low solution cost.  The idea of soft computing was initiated in 1981 BY Lotfi A. Zadeh.  Soft Computing is one multidisciplinary system as the fusion of the fields of Fuzzy Logic,
• 4.
  The Soft Computing– development history Soft Evolutionary Neural Fuzzy Computing Computing Network Logic Evolutionary Genetic Evolution Evolutionary Genetic Computing Programming Strategies Programming Algorithms
• 5.
  Goals of SoftComputing  to develop intelligent machines to provide solutions to real world problems, which are not modeled, or too difficult to model mathematically.  to exploit the tolerance for Approximation, Uncertainty, Imprecision, and Partial Truth in order to achieve close resemblance with human like decision making.  Well suited for real world problems where ideal solutions are not there.
• 6.
  Approximation : herethe model features are similar to the real ones, but not the same. Uncertainty : here we are not sure that the features of the model are the same as that of the entity (belief). Imprecision : here the model features (quantities) are not the same as that of the real ones, but close to them.  The guiding principle of soft computing is to exploit these tolerance to achieve tractability, robustness and low solution cost.  The role model for soft computing is the human mind.
• 7.
  PROBLEM SOLVING TECHNIQUES HARD COMPUTING SOFT COMPUTING Precise Models Approximate Models Symbolic Logic Reasoning Traditional Numerical Modeling and Search Approximate Reasoning Functional Approximation and Randomized Search
• 8.
  Hard computing Vs.Soft Computing Hard computing Soft Computing requires precisely state analytic mode l tolerant of imprecision, uncertainty, partial truth and approximation based on binary logic, crisp system, numerical analysis and crisp software based on fuzzy logic, neural sets, and probabilistic reasoning has the characteristics of precision and categoricity has the characteristics of approximation and dispositionality requires programs to be written can evolve its own programs uses two-valued logic. can use multivalued or fuzzy logic is deterministic. incorporates stochasticity
• 9.
  Soft ComputingConstituents Fuzzy Computing  Multivalued Logic for treatment of imprecision and vagueness  Neural Computing  Neural Computers mimic certain processing capabilities of the human brain  Genetic Algorithms  Genetic Algorithms (GAs) are used to mimic some of the processes observed in natural evolution and GAs are used to evolve programs to perform certain tasks. This method is known as "Genetic Programming" (GP).
• 10.
  From Conventional AIto Computational Intelligence  Conventional AI mostly involves methods now classified as machine learning, characterized by formalism and statistical analysis. This is also known as symbolic AI, logical AI, or neat AI. Methods include:  Expert systems: applies reasoning capabilities to reach a conclusion. An expert system can process large amounts of known information and provide conclusions based on them.  Case-based reasoning is the process of solving new problems based on the solutions of similar past problems.  Bayesian networks represents a set of variables together with a joint probability distribution with explicit independence assumptions.  Behavior-based AI: a modular method of building AI systems by hand.
• 11.
   Computational Intelligenceinvolves iterative development or learning. Learning is based on empirical data. It is also known as non-symbolic AI, scruffy AI, and soft computing. Methods mainly include:  Neural networks: systems with very strong pattern recognition capabilities.  Fuzzy systems: techniques for reasoning under uncertainty, have been widely used in modern industrial and consumer product control systems.  Evolutionary computation: applies biologically inspired concepts such as populations, mutation, and survival of the fittest to generate increasingly better solutions to the problem. These methods most notably divide into evolutionary algorithms and swarm intelligence.  Hybrid intelligent systems attempt to combine these two groups. It is thought that the human brain uses multiple
• 12.
  What is MachineLearning  To build computer systems that can adapt and learn from their experience.  Provides computers with the ability to learn without being explicitly programmed.  Focuses on the development of computer programs that can teach themselves to grow and change when exposed to new data.  Machine learning programs detect patterns in data and adjust program actions accordingly.  The process of machine learning is similar to that of data mining.  Instead of extracting data for human comprehension machine learning uses the data to improve the program's own understanding.
• 13.
   Facebook's NewsFeed changes according to the user's personal interactions with other users  In e-mail – spam messages.  Types of Machine Learning  Supervised learning --- where the algorithm generates a function that maps inputs to desired outputs. One standard formulation of the supervised learning task is the classification problem: the learner is required to learn (to approximate the behavior  of) a function which maps a vector into one of several classes by looking at several input-output examples of the function. Unsupervised learning --- which models a set of inputs: