Thursday, October 6, 2011

Artificial Neutral Networks JNTU PREVIOUS YEAR QUESTION PAPERS FOR ECE COLLECTIONS

Artificial Neutral Networks JNTU PREVIOUS YEAR QUESTION PAPERS COLLECTIONS 


Artificial Neutral Networks JNTU PREVIOUS YEAR QUESTION PAPERS COLLECTIONS 


1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'08-Set no 1


Code No: RR410405
Set No. 1


IV B.Tech I Semester Supplimentary Examinations, February 2008
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. (a) What are Artificial neural networks? What are their characteristics?
(b) Explain the historical development of Artificial neural networks? [16]


2. Discuss and compare all learning law’s. [16]


3. (a) Discuss adaptive filtering technique in single layer perceptron with its algorithms and convergence concept.
(b) Write about the working of LMS Algorithm with a numerical example. Assume suitable input and weight matrix. [8+8]


4. Discuss the working of single layer perceptron and multi layer perceptron with relevant algorithm and compare them. [16]


5. State and explain the Ex-OR problem? Also explain how to overcome it. [16]


6. Compare Radial basis network with multiplayer perceptron. Give suitable example. [16]


7. (a) Explain Maxican Hat Network with architecture.
(b) Write activation function used in Maxican Hat network. [10+6]


8. (a) What are the important applications in speech area?
(b) Discuss the use of feedback neural network to convert English text to speech. [8+8]


. . . . .












1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'08-Set no 2


Code No: RR410405
Set No. 2


IV B.Tech I Semester Supplimentary Examinations, February 2008
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. Compare and contrast the biological neuron and artificial neuron. [16]


2. Explain the training of Artificial and neural networks. [16]


3. (a) What is perceptron?
(b) Differentiate between perceptron representation and perceptron training? [6+10]


4. (a) Explain Baye’s classifier or Baye’s hypothesis testing procedure.
(b) Write about reduced strategy for optimum classification in Baye’s Classifier. [8+8]


5. State and explain the Ex-OR problem? Also explain how to overcome it. [16]


6. Discuss about the associative memory of Spatio-temporal pattern. [16]


7. (a) Define Firing Rule?
(b) What is a similarity Map? [8+8]


8. What are the direct applications of neural networks? Why are they called direct applications? [16]


. . . . .




















1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'08-Set no 3




Code No: RR410405
Set No. 3


IV B.Tech I Semester Supplimentary Examinations, February 2008
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. (a) What are Artificial neural networks? Where the neural networks implemented?
(b) Distinguish between supervised and unsupervised training? [8+8]


2. What are the basic learning laws? Explain the weight updation rules in each learning law. [16]


3. Write the algorithm for least mean square. Explain the working principle of it. [16]


4. (a) Explain Rosenblatts perceptron model?
(b) Differentiate between single layer and multi-layer perceptrons? [8+8]


5. Write short notes on the following:
(a) Hessian matrix
(b) Cross validation
(c) Feature detection. [4+6+6]


6. Write the following algorithm in associative memories.
(a) Retrieval algorithm
(b) Storage algorithm. [8+8]


7. (a) Explain briefly about Hamming network.
(b) What is the purpose of learning vector quantization? [6+10]


8. What is the difference between pattern recognition and classification? How artificial neural network is applied both? [16]


. . . . .








1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'08-Set no 4


Code No: RR410405
Set No. 4


IV B.Tech I Semester Supplimentary Examinations, February 2008
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. (a) What are Artificial neural networks? What are their characteristics?
(b) Explain the historical development of Artificial neural networks? [16]


2. What are the basic learning laws? Explain the weight updation rules in each learning law. [16]


3. (a) Discuss adaptive filtering technique in single layer perceptron with its algorithms and convergence concept.
(b) Write about the working of LMS Algorithm with a numerical example. Assume suitable input and weight matrix. [8+8]


4. Discuss the working of single layer perceptron and multi layer perceptron with relevant algorithm and compare them. [16]


5. (a) Write about the approximation made in Hessian based pruning techniques.
(b) Explain Weight decay procedure in complexity regularization. [8+8]


6. Discuss about the associative memory of Spatio-temporal pattern. [16]


7. (a) What is adaptive vector quantization? What is ‘learning vector quantization’?
(b) Explain the difference between pattern clustering and feature mapping.[10+6]


8. Explain the difficulties in the solution of traveling salesman problem by a feedback neural network. [16]


. . . . .










1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'07-Set no 1


Code No: RR410405
Set No. 1


IV B.Tech I Semester Supplementary Examinations, February 2007
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. (a) What are Artificial neural networks? What are their characteristics?
(b) Explain the historical development of Artificial neural networks? [16]


2. (a) Discuss the requirements of Learning Laws.
(b) What are different types of Hebbian learning? Explain basic Hebbian learning? [8+8]


3. (a) What is perceptron?
(b) Differentiate between perceptron representation and perceptron training? [6+10]


4. (a) Explain Rosenblatts perceptron model?
(b) Differentiate between single layer and multi-layer perceptrons? [8+8]


5. State and explain the Ex-OR problem? Also explain how to overcome it. [16]


6. (a) Explain Universal Approximation theorem.
(b) Explain about the Curse of dimensionality. [8+8]


7. A Maxnet consists of three inhibitory weights as 0.25. The net is initially activated by the input signals [0.1 0.3 0.9]. The activation function of the neuron is
X X > 0
F (X) = {
0 otherwise
Find the final winning neutron. [16]


8. What are the direct applications of neural networks? Why are they called direct applications? [16]


. . . . .






1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'07-Set no 3


Code No: RR410405
Set No. 3


IV B.Tech I Semester Supplementary Examinations, February 2007
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. (a) What are Artificial neural networks? Where the neural networks implemented?
(b) Distinguish between supervised and unsupervised training? [8+8]


2. What are the basic learning laws? Explain the weight updation rules in each learning law. [16]


3. State and prove the perceptron convergence algorithm. [16]


4. (a) Explain Rosenblatts perceptron model?
(b) Differentiate between single layer and multi-layer perceptrons? [8+8]


5. (a) Compute the Hessian matrix and determine whether it is positive definite for the function E(x) = (X1 - X2)2 + (1 - X1)2
(b) Discuss the network pruning techniques. [6+10]


6. (a) Write about generalized radial basis networks.
(b) Write approximation properties of radial basis function network. [8+8]


7. (a) Explain briefly about Hamming network.
(b) What is the purpose of learning vector quantization? [6+10]


8. Discuss the application of Artificial Neural Network on the field of control system and optimization. [16]


. . . . .












1: Total Question Paper of JNTU-IV B.Tech-ECE-Artificial Neutral Networks-Sup-Feb'07-Set no 4


Code No: RR410405
Set No. 4


IV B.Tech I Semester Supplementary Examinations, February 2007
ARTIFICIAL NEURAL NETWORKS
( Common to Electronics & Communication Engineering, Electronics &
Instrumentation Engineering, Bio-Medical Engineering and Electronics &
Telematics)


Time: 3 hours
Max Marks: 80


Answer any FIVE Questions
All Questions carry equal marks
. . . . .


1. Explain about the important Architectures of neural network. [16]


2. What are the basic learning laws? Explain the weight updation rules in each learning law. [16]


3. (a) What is perceptron?
(b) Differentiate between perceptron representation and perceptron training? [6+10]


4. (a) Explain Rosenblatts perceptron model?
(b) Differentiate between single layer and multi-layer perceptrons? [8+8]


5. (a) Write about the approximation made in Hessian based pruning techniques.
(b) Explain Weight decay procedure in complexity regularization. [8+8]


6. (a) Write about generalized radial basis networks.
(b) Write approximation properties of radial basis function network. [8+8]


7. (a) Define Firing Rule?
(b) What is a similarity Map? [8+8]


8. What neural network ideas are used in the development of phonetic typewriter? [16]


. . . . .

No comments:

Post a Comment