Scribd
Upload
37 views1 page

JanuaryFebruary 2023

The document is an exam paper for an Artificial Neural Networks course. It contains questions about neural network concepts like learning laws, memory, adaptive filtering, the XOR problem, network pruning, generalization, feature mapping, unsupervised vs supervised learning, attractors, Hopfield networks, Hebbian learning, neural network architectures, the perceptron convergence theorem, backpropagation, momentum in backpropagation, accelerated convergence, feature maps, self-organizing maps, learning vector quantization, neurodynamical models, restricted Boltzmann machines, and the storage capacity of Hopfield networks.

Uploaded by

etikelavaishnavi09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
37 views1 page

JanuaryFebruary 2023

The document is an exam paper for an Artificial Neural Networks course. It contains questions about neural network concepts like learning laws, memory, adaptive filtering, the XOR problem, network pruning, generalization, feature mapping, unsupervised vs supervised learning, attractors, Hopfield networks, Hebbian learning, neural network architectures, the perceptron convergence theorem, backpropagation, momentum in backpropagation, accelerated convergence, feature maps, self-organizing maps, learning vector quantization, neurodynamical models, restricted Boltzmann machines, and the storage capacity of Hopfield networks.

Uploaded by

etikelavaishnavi09
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Code No: 157AN R18

JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD


B. Tech IV Year I Semester Examinations, January/February - 2023
ARTIFICIAL NEURAL NETWORKS
(Electronics and Communication Engineering)
Time: 3 Hours Max. Marks: 75
JN
Note: i) Question paper consists of Part A, Part B.
ii) Part A is compulsory, which carries 25 marks. In Part A, Answer all questions.
iii) In Part B, Answer any one question from each unit. Each question carries 10 marks
and may have a, b as sub questions.
TU
PART – A
(25 Marks)
H
1.a) Describe the learning Laws in neural network. [2]
b) Explain about Long-term memory and short term memory in neural networks? [3]
c) State Adaptive filtering problem. [2]
U
d) Write about the XOR problem in neural network. [3]
e) What is Network Pruning? [2]
se
f) Explain about Generalization in neural networks. [3]
g) What is feature mapping? [2]
h) What is unsupervised learning ? How is it different from supervised learning? [3]
d
i) What are the different types of Attractors? [2]
j) What is a Hopfield network? [3]
pa
PART – B
(50 Marks)
pe
2. Explain in detail about Hebbian learning with its training algorithm. [10]
OR
3. Explain in detail about various Neural Network Architectures. [10]
rs
4. State and prove the perceptron convergence theorem. [10]
OR
5. Explain in detail about back propagation learning algorithm. [10]
20
6.a) Describe the merits and demerits of back propagation network.
b) Explain the significance of momentum factor in Back propagation network. [5+5]
OR
23
7. Describe the accelerated convergence of a neural network system. [10]

8. What are the basic features of feature Map? Explain about Self-Organization Maps. [10]
OR
9. Explain the Learning Vector Quantizer with a flow chart. [10]

10.a) Describe the properties of neurodynamical models.


b) Explain about restricted Boltzmen machines. [5+5]
OR
11. Explain in detail about the storage capacity of Hopfield network. [10]

---ooOoo---

You might also like