JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD
JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD B.Tech III ARTIFICIAL NEURAL NETWORKS Previous Question Paper (February - 2023 - R16)
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.
PART A
Compare neural network with human brain.
Answer
The human brain is a highly complex, parallel, and fault-tolerant biological system with approximately 10^11 neurons, whereas an artificial neural network is a simplified mathematical model that mimics this structure using interconnected processing nodes (neurons) operating in parallel to perform specific computational tasks.
What is error correction learning? Explain.
Answer
Error correction learning is a supervised learning process where the network adjusts its weights based on the difference between the actual output and the desired target output. The goal is to minimize this error signal over successive iterations, typically using algorithms like the Least Mean Square (LMS) rule.
What are the heuristics used in BP algorithm?
Answer
Sign in to view the complete answer paper.
Explain about single layer perceptron.
Answer
Sign in to view the complete answer paper.
What is delta rule in back propagation?
Answer
Sign in to view the complete answer paper.
How do you calculate back propagation error?
Answer
Sign in to view the complete answer paper.
What is the purpose of a self-organizing map?
Answer
Sign in to view the complete answer paper.
Write the basic steps in SOM algorithm.
Answer
Sign in to view the complete answer paper.
What is the purpose of dynamic systems?
Answer
Sign in to view the complete answer paper.
What do you mean by stability of equilibrium states?
Answer
Sign in to view the complete answer paper.
PART B
List and explain different neural network architectures in brief.
Answer
Sign in to view the complete answer paper.
What is learning? Explain the statistical nature of the learning process.
Answer
Sign in to view the complete answer paper.
Explain the differences between hebbian learning competitive learning techniques.
Answer
Sign in to view the complete answer paper.
What is Boltzmann learning? How is it different from other learning techniques?
Answer
Sign in to view the complete answer paper.
Write and explain Least Mean Square algorithm.
Answer
Sign in to view the complete answer paper.
How convergence is achieved in back propagation algorithm?
Answer
Sign in to view the complete answer paper.
State and explain adaptive filtering problem.
Answer
Sign in to view the complete answer paper.
Write the solution for XOR problem using BP algorithm.
Answer
Sign in to view the complete answer paper.
Compare and contrast Back propagation and Differentiation.
Answer
Sign in to view the complete answer paper.
Explain about cross validation techniques used in neural networks.
Answer
Sign in to view the complete answer paper.
List and explain various network pruning techniques.
Answer
Sign in to view the complete answer paper.
Write a brief note on Hessian Matrix and Generalization.
Answer
Sign in to view the complete answer paper.
Retrieval algorithm
Answer
Sign in to view the complete answer paper.
Storage algorithm.
Answer
Sign in to view the complete answer paper.
What are the two Basic Feature Mapping Models? Discuss.
Answer
Sign in to view the complete answer paper.
What is the purpose of learning vector quantization? Explain.
Answer
Sign in to view the complete answer paper.
What are Attractor neural networks? Explain.
Answer
Sign in to view the complete answer paper.
Explain manipulation process of Attractors as a Recurrent Network Paradigm.
Answer
Sign in to view the complete answer paper.
What are the modes of operation of a Hopfield network?.
Answer
Sign in to view the complete answer paper.
Explain the algorithm for storage of information in a Hopfield network.
Answer
Sign in to view the complete answer paper.