Syllabus B Tech Computer Science Eighth Semester Soft Computing CS8001

Computer-Science-Engineering-8

Syllabus B Tech Computer Science Eighth Semester Soft Computing CS8001

The concepts developed in this course will aid in quantification of several concepts in Computer Science Engineering that have been introduced at the Engineering courses. Technology is being increasingly based on the latest Syllabus B Tech Computer Science Eighth Semester Soft Computing CS8001 is given here.

The objective of this course Syllabus B Tech Computer Science Eighth Semester Soft Computing CS8001 is to develop ability and gain insight into the process of problem-solving, with emphasis on thermodynamics. Specially in following manner: Apply conservation principles (mass and energy) to evaluate the performance of simple engineering systems and cycles. Evaluate thermodynamic properties of simple homogeneous substances. Analyze processes and cycles using the second law of thermodynamics to determine maximum efficiency and performance. Discuss the physical relevance of the numerical values for the solutions to specific engineering problems and the physical relevance of the problems in general and Critically evaluate the validity of the numerical solutions for specific engineering problems. More precisely, the objectives are:

  • To enable young technocrats to acquire mathematical knowledge to understand Laplace transformation, Inverse Laplace transformation and Fourier Transform which are used in various branches of engineering.
  • To introduce effective mathematical tools for the Numerical Solutions algebraic and transcendental equations.
  • To acquaint the student with mathematical tools available in Statistics needed in various field of science and engineering.

CS 8001 – Soft Computing

Unit 1
Introduction: Introduction to soft computing, application areas of soft computing, classification of soft computing techniques, structure & functioning of biological brain & Neuron, and concept of learning/training. Model of an Artificial Neuron, transfer/activation functions, perceptron, perceptron learning model, binary & continuous inputs, linear separability.
Unit 2
Multilayer Neural Networks: Feed Forward network – significance, training, loss function, Back-Propagation algorithm, convergence & generalization, momentum, applications. Feedback network -Hopfield Nets: architecture, energy functions, training algorithms & examples, competitive learning, self-organizing maps. Introduction to CNN and RNN network.
Unit 3
Fuzzy Systems: fuzzy set theory, fuzzy sets and operations, membership functions, concept of fuzzy relations and their composition, concept of fuzzy Measures. Fuzzy logic: fuzzy rules, inferencing. Fuzzy Control system: selection of membership functions, Fuzzyfication, rule based design & inferencing, defuzzyfication, applications of fuzzy system.
Unit 4
Genetic algorithm: concepts, creation of offspring, working principle, encoding, fitness functions, reproduction, genetic modeling. Generation cycle & convergence of GA, application areas of GA.
Unit 5
Advanced soft computing techniques: Rough Set Theory – Introduction, Set approximation, Rough membership, Attributes, optimization. SVM – Introduction, obtaining the optimal hyper plane, linear and nonlinear SVM classifiers. Introduction to Swarm Intelligence, Swarm Intelligence Techniques: Ant Colony Optimization, Particle Swarm Optimization, Bee Colony Optimization etc.

Books Recommended

1. S.N. Sivanandam & S.N. Deepa, Principles of Soft Computing, Wiley Publications
2. S, Rajasekaran & G.A. Vijayalakshmi Pai, Neural Networks, Fuzzy Logic & Genetic Algorithms, Synthesis & applications, PHI Publication
3. Bose, Neural Network fundamental with Graph , Algo.& Appl, TMH Kosko: Neural Network & Fuzzy System, PHI Publication
4. Klir & Yuan ,Fuzzy sets & Fuzzy Logic: Theory & Appli.,PHI Pub. Hagen, Neural Network Design, Cengage Learning.