JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD IV B.TECH II SEM–REGULAR/SUPPLEMENTARY EXAMINATIONS MAY - 2010 NEURAL NETWORKS & FUZZY LOGIC (MECHANICAL ENGINEERING) (MECHATRONICS) Time: 3hours Max.Marks:80 Answer any FIVE questions All questions carry equal marks --1.
What is a neural network? Explain clearly various models of a neuron.
[16]
2.
Discuss the Boltzmann learning rule and competitive learning.
[16]
3.
State and prove the perceptron convergence theorem.
[16]
4.
State and explain the generalized delta learning rule applied in back propagation algorithm. [16]
5.a) b)
Describe the pattern sequence encoding in temporal associative memory. Explain the traveling sales man problem of minimization of the tour length. Consider a 5 city problem. [8+8]
6.a) b)
Explain Crisp relations. Explain Fuzzy relations.
7.
List the various defuzzification techniques. Explain each of them in detail.
[16]
8.
Explain the step-by-step procedure in designing of a fuzzy logic controller.
[16]
[8+8]
---o0o---
www.QuestionPaperDownload.com
www.QuestionPaperDownload.com
Code.No: R05421405
R05
SET-2
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD IV B.TECH II SEM–REGULAR/SUPPLEMENTARY EXAMINATIONS MAY - 2010 NEURAL NETWORKS & FUZZY LOGIC (MECHANICAL ENGINEERING) (MECHATRONICS) Time: 3hours Max.Marks:80 Answer any FIVE questions All questions carry equal marks --1.a) b)
What is the significance of momentum term in back propagation learning. Why convergence is not guaranteed for the back propagation-learning algorithm. [8+8]
2.
What are the general equations for the hyper planes in two and three dimensions in space? What geometric figures do these equations describe? [16]
3.
What are the characteristics of feed forward neural networks? What is the significance of number of neurons in the input and output layers. [16]
4.
Derive the learning rule for Back Propagation network. What are the major drawbacks? Suggest solutions, to over come these drawbacks. [16]
5.a) b)
State and prove bi-directional associative memory energy theorem. With suitable diagram, explain the learning of Boltzmann’s machines.
[8+8]
6.a) b)
Explain Union intersection and Complement with reference to Fuzzy sets. Explain Union intersection and Complement with reference to crisp sets.
[8+8]
7.
Define defuzzification. Explain different methods of defuzzification.
[16]
8.
Give examples of application of neural networks in Load Forecasting.
[16]
---o0o---
www.QuestionPaperDownload.com
www.QuestionPaperDownload.com
Code.No: R05421405
R05
SET-3
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD IV B.TECH II SEM–REGULAR/SUPPLEMENTARY EXAMINATIONS MAY - 2010 NEURAL NETWORKS & FUZZY LOGIC (MECHANICAL ENGINEERING) (MECHATRONICS) Time: 3hours Max.Marks:80 Answer any FIVE questions All questions carry equal marks --1.a) b)
Differentiate single layer and multilayer networks. Generate the output of AND-NOT function using McCulloch-Pitts Neuron.
2.
Describe the four unsupervised learning laws.
3.
Explain the step by step procedure involved in classification and training of patterns using i) Continuous perceptron algorithm. ii) Multicategory single layer perceptron. [16]
4.
Explain the basic functional units. Explain how to solve pattern recognition tasks using functional units. [16]
5.a) b)
Discuss the stability of equilibrium states. Draw and explain the architectural graph of a Hopfield network consisting of N = 4 neurons. [8+8]
6.a) b)
Define Union, Intersection, Complement and composition of fuzzy relations. Define Cartesian product of crisp relations.
[8+8]
7.
List the main components of fuzzy logic controller. Explain each of them in detail.
[16]
Explain Neural Network based Controller for Induction Motor.
[16]
8.
---o0o---
www.QuestionPaperDownload.com
[8+8] [16]
www.QuestionPaperDownload.com
Code.No: R05421405
R05
SET-4
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD IV B.TECH II SEM–REGULAR/SUPPLEMENTARY EXAMINATIONS MAY - 2010 NEURAL NETWORKS & FUZZY LOGIC (MECHANICAL ENGINEERING) (MECHATRONICS) Time: 3hours Max.Marks:80 Answer any FIVE questions All questions carry equal marks --1.
Clearly distinguish between auto association and hetero association. Describe the Hebbian learning rule. [16]
2.a) b)
What are Kohonen layer and Grossberg layer? Explain Kohonen layer learning.
3.a) b)
Describe the Rosneblatt’s perceptron model of an artificial neuron. Distinguish between linearly separable and linearly inseparable problems. Give examples for each. [8+8]
4.
Explain the various methods used to extend back propagation.
5.a) b)
Design a Hopfield network to solve a five city traveling salesperson problem. Write the Algorithm for ARTI Network.
6.
Write short notes on the following: i) Fuzzification interface. ii) Knowledge base in fuzzy logic controller.
[8+8]
[16]
[8+8]
[16]
7. a) b)
Write short notes on the following: Knowledge base in fuzzy logic control system. Decision making logic in fuzzy logic control system.
8.
What are the various active building blocks of neural networks? Explain the current mirror and inverter based neuron in detail. [16]
State and prove the perceptron convergence theorem. [16]. 4. State and explain the generalized delta learning rule applied in back propagation. algorithm. [16].
Explain how in a population of telomere deficient cells, the loss of p53 facilitates. the development of cancer? [16] ? ? ? ? ? www.questionpaperdownload.com ...
Page 2 of 8. Code No: R05420306 R05 Set No. 2. Figure 6. 7. (a) Explain the application of industrial Robots in stamping - press operation. (b) What are the ...
iii. the energy stored. 7. Explain about the parameters of the open wire line at high frequencies? [16]. 8. (a) List out the applications of transmission lines.
Explain universal soil loss equation (USLE) and estimation of various factors in. USLE. [16]. 5. Explain how remote sensing and GIS is useful for preparation of ...
(a) Explain synchronus an asynchronus time division multiplexing of PCM sig- nals? (b) âPulse modulation systems are not digital, where as, pulse-code ...
Use partial fraction method to express X(z) as a sum of terms. iii. Determine x(n) [4+12]. 2. (a) Find the Fourier series of the wave shown in figure 1a. Figure 1a.
constructors for the hash table class. (b) Write a C++ program to implement a search operation in a hash table. [6+10]. 7. Write and explain a non recursive ...
1.a) Discuss various customer myths and realities in software development. b) What do you mean by software affliction? [8+8]. 2.a) Explain how would you select ...
illustrate overloaded constructor and copy constructor? [5+4+7]. 3.a) Difference between Static Binding and Dynamic Binding with example? b) Explain at least ...
Explain different phases of action potential of cardiac muscle fibre of heart? [16]. 4. Explain pulmonary ventilation in detail and sketch the neat diagram of lungs ...
(b) What is cipher feedback mode? Why it is used? [10+6] ? ? ? ? ? Page 1 of 1. B Tech 3-1 R05 CN Question Paper.pdf. B Tech 3-1 R05 CN Question Paper.pdf.
plates is 2cm and the accelerating voltage is 1000volts. [8+8] ? ? ? ? ? 1. www.QuestionPaperDownload.com www.QuestionPaperDownload.com. Page 1 of 4 ...
Construct a FA for the following Right Linear Grammar (R.L.G) and write the. conversion procedure? S A â 0. A A â10 / â. [16]. 5.a) Describe the language in ...
where X(k) is the 10-point DFT of x(n). (c) Find the 10-point sequence y(n) that has a DFT Y(K)=X(K)W(K) where. X(K)is the 10-point DFT of the sequence.
(a) Explain how a server generates dynamic content. (b) Give a note on request time errors. [8+8]. 7. Java server pages simplify the delivery of dynamic web ...
What are the models available in supply chain management? Explain any one of. the model with a suitable example. [16]. 7. Define data mining and describe its ...