07A70210 Neural Networks & Fuzzy Logic B.Tech Question Paper : scce.ac.in
Name of the College : SREE CHAITANYA COLLEGE OF ENGINEERING
University : JNTUH
Department : ELECTRICAL AND ELECTRONICS ENGINEERING
Subject Code/Name : 07A70210/NEURAL NETWORKS AND FUZZY LOGIC
Year/Sem : IV/II
Website : scce.ac.in
Document Type : Model Question Paper
Download Model/Sample Question Paper : https://www.pdfquestion.in/uploads/scce.ac.in/4923-07A70210-NEURALNETWORKSANDFUZZYLOGIC.pdf
SCCE Neural Networks & Fuzzy Logic Question Paper
Code No: 07A70210
R07 Set No. 2
IV B.Tech I Semester Examinations,December 2011
Related : Sree Chaitanya College Of Engineering 07A70206 High Voltage Engineering B.Tech Question Paper : www.pdfquestion.in/4925.html
Common to Aeronautical Engineering, Instrumentation And Control Engineering, Electrical And Electronics Engineering
Time: 3 hours
Max Marks: 80
Answer any FIVE Questions :
All Questions carry equal marks :
1. What are the various active building blocks of neural networks? Explain the current mirror and inverter based neuron in detail. [16]
2. Distinguish between the feed forward and feedback neural networks. Compare their input-output mapping. [16]
3. (a) Define classical set
(b) Differentiate fuzzy set from classical set and name the properties of classical (crisp) sets. [8+8]
4. Using your own intuition and your own definitions of the universe of discourse, plot fuzzy membership functions for the following variables
Age of people
(a) Very Young.
(b) Young.
(c) Middle-aged.
(d) old.
(e) Very old. [16]
5. Suggest and explain activation model, learning method for solving non-linear activation problems. [16]
6. (a) What is XOR problem? Draw and explain the architectural graph of network for solving the XOR problem.
(b) Discuss about output representation and decision rule. [8+8]
7. (a) Construct a Hopfield network to associate 3×3 input images with dots and dashes.
(b) How many spurious attractors does this network have i.e how many patterns other than dots and dashes are stable attractors?
(c) How many input errors can this network withstand i.e how much can the image of a dot (or dash) be corrupted while still allowing the network to retrieve a dot (or dash)? [16]
8. Discuss the operation of single neuron system. A neuron j receives inputs from four other neurons whose activity levels are 10, -20, 4 and -2. The respective synaptic weights of the neuron j are 0.8, 0.2, -1.0, and -0.9.
Calculate the output of neuron for the following two situations
(a) The neuron is linear.
(b) The neuron is represented by a McCulloch-Pitt s model. Assume that the bias applied to the neuron is zero. [16]
Code No: 07A70210
R07 Set No. 4
1. (a) Describe the pattern sequence encoding in temporal associative memory.
(b) Explain the traveling sales man problem of minimization of the tour length. Consider a 5 city problem. [8+8]
2. Write short notes on the following.
(a) Fuzzification interface.
(b) Knowledge base in fuzzy logic controller. [16]
3. State and prove the perceptron convergence theorem. [16]
4. Using your own intuition, develop fuzzy membership functions on the real line for the fuzzy number “approximately 2 to approximately 8”, using the following function shapes
(a) Symmetric triangles
(b) Trapezoids.
(c) Gaussian functions. [16]
5. Write short notes on the following:
(a) Adaptive fuzzy systems.
(b) Fuzzy neural networks. [8+8]
6. (a) With help of suitable diagram, discuss the dynamics of the Hopfield network.
(b) Taking a three-node net, why cannot the following states V1 V2 V3 = 000, 011, 110 and 101 be made stable well. [8+8]
7. Investigate the use of back-propagation learning using a sigmoidal nonlinearity to achieve one-to-one mapping as given below
Compute the following :
(a) Set up two sets of data, one for network training and other for testing.
(b) Use the training data set to compute the synaptic weights of the network, assumed to have a single hidden layer. [16]
IV B.Tech I Semester Examinations,December 2011 :
Neural Networks And Fuzzy Logic :
1. (a) Explain the properties of Commutativity,Associativity,Distributivity,Idempotence, Identity with respect to crisp sets
(b) Given that A=0.2/3 + 0.5/4 + 0.8/5 and B=0.8/5 + 0.2/8, determine the Cartesian product of the two sets; A x B.
2. Explain the following terms :
(a) Resting potential.
(b) Nernst equation.
(c) Action potential.
(d) Refractory periods.
(e) Chemical synapses. [16]
3. Write notes on :
(a) Error correction learning.
(b) Reinforcement learning. [8+8]
4. What is backpropagation? With a schematic two-layer feed forward neural net- work, derive its learning algorithm. Also discuss its learning diculties and im- provements. [16]
5. Design and develop a pressure process control by FLC model. Formulate necessary membership functions and required fuzzy rules for the application. [16]
6. (a) State two assumptions in fuzzy control system design
(b) Explain the fuzzy logic is being implemented for image processing. [8+8]
7. (a) Explain the working of a hopeld network with a neat sketch of its architecture
(b) A hopeld network made up of 5 neurons, which is required to store the following three fundamental memories
8. Implement the single Discrete Perceptron training algorithm for C = 1 for the discrete Perceptron dichotomizer which provides the following classication of six patterns