Question Paper: Soft Computing Question Paper - May 16 - Information Technology (Semester 8) - Mumbai University (MU)
0

INSTRUCTIONS
(1) Assume appropriate data and state your reasons
(2) Marks are given to the right of every question
(3) Draw neat diagrams wherever necessary

1(a) Give the application scope of Neural Networks. 5 marks

1(b) What is activation function? Discuss the role of Sigmoidal activation function in back propagation. 5 marks

1(c) Define soft computing. Distinguish between soft computing and hard computing? 5 marks

1(d) Explain in short the membership functions in Fuzzy Set. 5 marks

2(a) Explain in detail the back-propagation algorithm. 10 marks

2(b) Discuss fuzzy composition techniques with suitable example. 10 marks

3(a) Explain in detail the Genetic Algorithm based back propagation network. 10 marks

3(b) Two fuzzy relations are given by *\begin{matrix} & \begin{matrix} y_1 &y_2 \end{matrix}\ R = \begin{matrix} x_1\ x_2\ \end{matrix} & \begin{bmatrix} 0.6 &0.3 \ 0.2 &0.9\ \end{bmatrix} \end{matrix}</script> <mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd ></mtd><mtd><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><msub><mi>z</mi><mn>1</mn></msub></mtd><mtd><msub><mi>z</mi><mn>2</mn></msub></mtd><mtd><msub><mi>z</mi><mn>3</mn></msub></mtd></mtr></mtable></mtd></mtr><mtr><mtd><mi>S</mi><mo>=</mo><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><msub><mi>y</mi><mn>1</mn></msub></mtd></mtr><mtr><mtd><msub><mi>y</mi><mn>2</mn></msub></mtd></mtr></mtable></mtd><mtd><mrow><mo>[</mo><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><mn>1</mn></mtd><mtd><mn>0.5</mn></mtd><mtd><mn>0.3</mn></mtd></mtr><mtr><mtd><mn>0.8</mn></mtd><mtd><mn>0.4</mn></mtd><mtd><mn>0.7</mn></mtd></mtr></mtable><mo>]</mo></mrow></mtd></mtr></mtable>[/itex]" role="presentation" style="font-size: 125%; text-align: center; position: relative;">z1z2z3S=y1y2[10.50.30.80.40.7]<math xmlns="http://www.w3.org/1998/Math/MathML" display="block"><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd></mtd><mtd><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><msub><mi>z</mi><mn>1</mn></msub></mtd><mtd><msub><mi>z</mi><mn>2</mn></msub></mtd><mtd><msub><mi>z</mi><mn>3</mn></msub></mtd></mtr></mtable></mtd></mtr><mtr><mtd><mi>S</mi><mo>=</mo><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><msub><mi>y</mi><mn>1</mn></msub></mtd></mtr><mtr><mtd><msub><mi>y</mi><mn>2</mn></msub></mtd></mtr></mtable></mtd><mtd><mrow><mo>[</mo><mtable rowspacing="4pt" columnspacing="1em"><mtr><mtd><mn>1</mn></mtd><mtd><mn>0.5</mn></mtd><mtd><mn>0.3</mn></mtd></mtr><mtr><mtd><mn>0.8</mn></mtd><mtd><mn>0.4</mn></mtd><mtd><mn>0.7</mn></mtd></mtr></mtable><mo>]</mo></mrow></mtd></mtr></mtable>[/itex]<script type="math/tex; mode=display" id="MathJax-Element-2">\begin{matrix} & \begin{matrix} z_1 &z_2 &z_3\ \end{matrix}\ S = \begin{matrix} y_1\ y_2\ \end{matrix} & \begin{bmatrix} 1 &0.5 & 0.3\ 0.8 &0.4 & 0.7\ \end{bmatrix} \end{matrix}</script> 10 marks

4(a) What is linear Separability? Justify-XOR function is non-linearly separable by a single decision boundary line. 10 marks

4(b) Describe in detail the formation of inference rules in a Mamdani Fuzzy Inference System. 10 marks

5(a) State and Justify the role of vigilance parameters in ART network. 10 marks

5(b) Implement OR funtion using perceptron networks for bipolar inputs and targets. 10 marks

6(a) Write short note on Defuzzification. 5 marks

6(b) Write short note on Delta Learning Rule. 5 marks

6(c) Explain applications of Hybrid Systems. 5 marks

6(d) Explain in short Radial Basis Fundtion Network. 5 marks