## Neural Networks and Fuzzy Systems - Dec 2013

### Electronics Engineering (Semester 8)

TOTAL MARKS: 100

TOTAL TIME: 3 HOURS
(1) Question 1 is compulsory.

(2) Attempt any **four** from the remaining questions.

(3) Assume data wherever required.

(4) Figures to the right indicate full marks.
**1 (a)** Compare RBFN and MLP network.(5 marks)
**1 (b)** State application of Kohenen self organising maps.(5 marks)
**1 (c)** Explain Intersections and Union of fuzzy set(5 marks)
**1 (d)** What are various characteristics of ANN(5 marks)
**2 (a)** What is learning process ? What do you mean by supervised and unsupervised learning with suitable example(10 marks)
**2 (b)** Explain RBF to solve XOR problem(10 marks)
**3 (a)** Write an algorithm for back propagation and explain about the updation of weight process(10 marks)
**3 (b)** Draw the architecture of Hopfield network. Explain how it is more stable than the BPN.(10 marks)
**4 (a)** Explain the following term :

(i) ANFIS

(ii) Brain state in box mode(10 marks)
**4 (b)** Explain perceptron convergence theorem(10 marks)
**5 (a)** Explain steepest descent algorithm(10 marks)
**5 (b)** Explain fuzzy membership functions(10 marks)
**6 (a)** Distinguish between self organized learning Networks and Kohenen network(10 marks)
**6 (b)** If A is the fizzy set defined by

$$A=\frac{0.5}{x_{1}}+\frac{0.4}{x_{0}}+\frac{0.7}{x_{3}}+\frac{0.8}{x_{4}}+\frac{1}{x_{5}} $$

List all α cuts of A.(10 marks)

### Write short notes on (any four).

**7 (a)** Fuzzy controller(5 marks)
**7 (b)** Learning factors(5 marks)
**7 (c)** Boltzman machine(5 marks)
**7 (d)** Neurodynamic model(5 marks)
**7 (e)** LMS algorithm(5 marks)
**7 (f)** Fuzzy relation and functions.(5 marks)