CS 8th sem Soft Computing Syllabus CS 801 Soft Computing Syllabus

RGTU/RGPV CS -801 Soft Computing Syllabus

 RGTU/RGPV Soft Computing SYLLABUS

Computer Science and Engineering CS 8th Semester Syllabus,

Unit – I
  Soft Computing : Introduction of soft computing, soft computing vs. hard computing, various types of soft computing techniques, applications of soft computing. Artificial Intelligence : Introduction, Various types of production systems, characteristics of production systems, breadth first search, depth first search techniques, other Search Techniques like hill Climbing, Best first Search, A* algorithm, AO* Algorithms and various types of control strategies. Knowledge representation issues, Prepositional and predicate logic, monotonic and non monotonic reasoning, forward Reasoning, backward reasoning, Weak & Strong Slot & filler structures, NLP.

Unit – II
  Neural Network : Structure and Function of a single neuron: Biological neuron, artificial neuron, definition of ANN, Taxonomy of neural net, Difference between ANN and  human brain, characteristics and applications of ANN, single layer network, Perceptron training algorithm, Linear separability, Widrow & Hebb;s learning rule/Delta rule, ADALINE, MADALINE, AI v/s ANN.
Introduction of MLP, different activation functions, Error back propagation algorithm, derivation of BBPA, momentum, limitation, characteristics and application of EBPA,

Unit – III
  Counter propagation network, architecture, functioning & characteristics of counter Propagation network, Hopfield/ Recurrent network, configuration, stability constraints, associative memory, and characteristics, limitations and applications. Hopfield v/s Boltzman machine. Adaptive Resonance Theory: Architecture, classifications, Implementation and training. Associative Memory.

Unit – IV
  Fuzzy Logic: Fuzzy set theory, Fuzzy set versus crisp set, Crisp relation & fuzzy relations, Fuzzy systems: crisp logic, fuzzy logic, introduction & features of membership functions,  Fuzzy rule base system : fuzzy propositions, formation, decomposition & aggregation of fuzzy rules, fuzzy reasoning, fuzzy inference systems, fuzzy decision making & Applications of fuzzy logic.

Unit – V
  Genetic algorithm : Fundamentals, basic concepts, working principle, encoding, fitness function, reproduction, Genetic modeling: Inheritance operator, cross over, inversion & deletion, mutation operator, Bitwise operator, Generational Cycle, Convergence of GA, Applications & advances in GA, Differences & similarities between GA & other traditional methods.

CS -801 Soft Computing Syllabus References : 

• S, Rajasekaran & G.A. Vijayalakshmi Pai, Neural Networks, Fuzzy Logic & Genetic Algorithms, Synthesis & applications, PHI Publication.   
• S.N. Sivanandam & S.N. Deepa, Principles of Soft Computing, Wiley Publications   
• Rich E and Knight K, Artificial Intelligence, TMH, New Delhi.   
• Bose, Neural Network fundamental with Graph , Algo.& Appl, TMH   
• Kosko: Neural Network & Fuzzy System, PHI Publication   
• Klir & Yuan ,Fuzzy sets & Fuzzy Logic: Theory & Appli.,PHI Pub.   
• Hagen, Neural Network Design, Cengage Learning

IT 8th sem Soft Computing Syllabus IT802 Soft Computing Syllabus

RGTU/RGPV IT 802 Soft Computing Syllabus

RGTU/RGPV Soft Computing SYLLABUS

Information Technology IT 8th Semester Syllabus

Unit I: Introduction to Neural Network: Concept, biological neural network, evolution of artificial neural network, McCulloch-Pitts neuron models, Learning (Supervise & Unsupervise) and activation function, Models of ANN-Feed forward network and feed back network, Learning Rules- Hebbian, Delta, Perceptron Learning  and Windrow-Hoff, winner take all.

Unit II: Supervised Learning: Perceptron learning,- Single layer/multilayer, linear Separability, Adaline, Madaline, Back propagation network, RBFN. Application of Neural network in forecasting, data compression and image compression. 

Unit III: Unsupervised learning: Kohonen SOM (Theory, Architecture, Flow Chart, Training Algorithm) Counter Propagation (Theory , Full Counter Propagation NET and Forward only counter propagation net), ART (Theory, ART1, ART2). Application of Neural networks in pattern and face recognition, intrusion detection, robotic vision.

Unit IV: Fuzzy  Set:  Basic Definition and Terminology, Set-theoretic Operations, Member Function,
Formulation and Parameterization, Fuzzy rules and fuzzy Reasoning, Extension Principal and Fuzzy Relations, Fuzzy if-then Rules, Fuzzy Inference Systems. Hybrid system including neuro fuzzy hybrid, neuro genetic hybrid and fuzzy genetic hybrid, fuzzy logic controlled GA. Application of Fuzzy logic in solving engineering problems.

Unit V: Genetic Algorithm: Introduction to GA, Simple Genetic Algorithm, terminology and operators of GA (individual, gene, fitness, population, data structure, encoding, selection, crossover, mutation, convergence criteria). Reasons for working of GA and Schema theorem, GA optimization problems including JSPP (Job shop scheduling problem), TSP (Travelling salesman problem), Network design routing, timetabling problem. GA implementation using MATLAB.

IT 830 Soft Computing References:-

•  S.N. Shivnandam, “Principle of soft computing”, Wiley.   
• S. Rajshekaran and G.A.V. Pai, “Neural Network , Fuzzy logic And Genetic Algorithm”, PHI.   
• Jack M. Zurada, “Introduction to Artificial Neural Network System” JAico Publication.   
• Simon Haykins, “Neural Network- A Comprehensive Foudation”   
• Timothy J.Ross, “Fuzzy logic with Engineering Applications”, McGraw-Hills 1.

IT 830 Soft Computing List of Experiment:-

• Form a perceptron net for basic logic gates with binary input and output.
• Using Adaline net, generate XOR function with bipolar inputs and targets.   
• Calculation of new weights for a Back propagation network, given the values of input pattern, output pattern, target output, learning rate and activation function.   
• Construction of Radial Basis Function Network.   
• Use of Hebb rule to store vector in auto associative neural net.   
• Use of ART algorithm to cluster vectors.   
• Design fuzzy inference system for a given problem. 
• Maximize the function y =3x**2+ 2 for some given values of x using Genetic algorithm.   
• Implement Travelling salesman problem using Genetic Algorithm.   
• Optimisation  of problem like Job shop scheduling  using Genetic algorithm

ME/M.Tech. Computer Tech. & Applications, Software Systems 2nd sem MCTA 201 Soft Computing Syllabus

Tags: Soft Computing Syllabus, ME/M.Tech 2nd semester Syllabus, MCTA 201 Syllabus, ME/M.Tech Second Semester Syllabus, Computer Tech. & Applications M.Tech Syllabus, Software Systems M.Tech Syllabus

Rajiv Gandhi Technological University, Bhopal (MP)
Computer Tech. & Applications (UTD, RGTU, Bpl)
Software Systems SATI (Vidisha)
ME/M.Tech. 1st FIRST SEMESTER SYLLABUS
MCTA 201 Soft Computing Syllabus

Unit 1
ARTIFICIAL NEURAL NETWORKS : Basic concepts - Importance of tolerance of imprecision and uncertainty. Biological and artificial neuron, Single layer perception - Multilayer Perception - Supervised and Unsupervised learning – Back propagation networks - Kohnen's self organizing networks - Hopfield network.

Unit 2
FUZZY SYSTEMS : Introduction, History of the Development of Fuzzy Logic, Fuzzy sets and Fuzzy reasoning - Fuzzy matrices - Fuzzy functions - Decomposition - Fuzzy automata and languages - Fuzzy control methods - Fuzzy decision making.

Unit 3
NEURO - FUZZY MODELING : Adaptive networks based Fuzzy interface systems - Classification and Regression Trees - Data clustering algorithms - Rule based structure identification - Neuro-Fuzzy controls - Simulated annealing – Evolutionary computation.

Unit 4
GENETIC ALGORITHMS: Survival of the Fittest - Fitness Computations - Cross over - Mutation - Reproduction - Rank method - Rank space method.

Unit 5
SOFT COMPUTING AND CONVENTIONAL AI : AI search algorithm - Predicate calculus - Rules of interference – Semantic networks - Frames - Objects - Hybrid models – Applications, MATLAB Toolbox - An Overview.

Reference Books:
1. S. Rajasekran, G.A. Vijayalaxmi Pai “Neural Network, Fuzzy Logic and Genatic
Algorithm”.
2. Martin T. Hagan, Howard B. Demuth, Mark Beale “Neural Network Design, VPH
Pub.
3. Bert Kosko “Neural Networks and Fuzzy Systems” PHI Pub.
4. Keeman “Learning & soft computing”, Pearson
5. Philip d. W asserman “Neural Computing”, Van Nastrand Reinhold pub.