AKTU Neural Networks & Fuzzy System (KEE056) Question Paper 2022-23

Note: Attempt all Sections. If you require any missing data, then choose suitably.

Section A

Q1. Attempt all questions in brief · 2 × 10 = 20 marks

1. Write the applications of artificial neural network.
2. Draw 2-4-2 feed forward neural network.
3. List various tuning parameters in back propagation.
4. If the net input to an output neuron is 0.54, compute its output when the activation function is binary sigmoidal.
5. Describe the difference between fuzzy and crisp set.
6. Explain linguistic variables in brief.
7. Define universal set in fuzzy set theory with example.
8. Describe fuzzy inference system.
9. Describe strong α-cut fuzzy set.
10. Define the L-R type Fuzzy numbers.

Section B

Q2. Attempt any three of the following · 10 × 3 = 30 marks

1. Compare and contrast Biological Neuron and Artificial Neuron with suitable diagram.
2. Explain the importance of sigmoidal function in Backpropagation algorithm. Drive the equation for output layer weight adjustment for Back-Propagation Neural Network: ΔW = η {OH} .
3. What are the components of fuzzy logic control and explain them in detail with block diagram?
4. Suppose an engineer is addressing a problem in the power control of a mobile cellular telephone transmitting to its base station. Let MP be the medium-power fuzzy set and HP be the high-power set. Let the universe of discourse be composed of discrete units of 𝑑𝐵 ൈ 𝑚 , that is, 𝑋 ൌ ሼ0, 1, 2, … … .10ሽ . The membership functions for these two fuzzy sets are shown in figure. For these two fuzzy sets demonstrate union, intersection, complement and the difference.
5. Explainthe structure of a neural expert system in details.

Section C

Q3

Attempt any one part of the following · 10 × 1 = 10 marks

1. Analyze the necessity of Activation function in ANN. Characterize different types of activation functions used in ANN.
2. Train a hetero-associative memory network using Hebb rule to store input row vector s = (s , s , s , s ) to the output row vector t = (t , t ). The vector pairs are given in table below: Input Targets s s s s t t st nd rd th

Q4

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain step by step procedure of back propagation learning algorithm in detail.
2. The input to a single input neuron is 2, weight is 2.3 and its bias is -3. Examine the neuron output for different transfer functions:
   (i) Unit step with threshold value = 1
   (ii) Linear with slope m = 2
(iii) Bipolar Sigmoidal with λ = 0.5

Q5

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain the meaning of defuzzification in fuzzy logic controller. Describe different methods of defuzzification process.
2. A Rocket was launched carrying a satellite which will be reaching a distance of
   22,300 miles at a speed of 4.9 m/s from Earth. During its path, the average speed (A)
   for every 20-minute intervals and fuel consumed (B) for every 2000 miles traveled is
   monitored. Given the fuzzy sets that follow.
   0.6 0.7 0.9 0.8 0.8 0.7
   ሚ ൌ ൜
   𝐴 ൅ ൅ ൅ ൅ ൅ ൠ
   0.9 0.8 0.7 0.6 0.3 0.2
   ෨ ൌ ൜
   𝐵 ൅ ൅ ൅ ൅ ൅ ൠ
   Determine a relation 𝑅 that relates the average speed and fuel consumed.

Q6

Attempt any one part of the following · 10 × 1 = 10 marks

1. For an air conditioner, what will be the input and output in a Fuzzy controller? Explain in details of Fuzzy Logic Controller for Classroom Air Conditioner.
2. Explain with example, the importance of fuzzy logic system in your own healthcare.

Q7

Attempt any one part of the following · 10 × 1 = 10 marks

1. Explain synergy between neural-fuzzy system. Summarize different characteristics of it.
2. Analyze the different steps of the Fuzzy-backpropagation training.

Other years

More AKTU Soft Computing papers on LearnAIFast.

This paper is reproduced for study purposes only. Copyright belongs to AKTU. Source: the question paper bank of ABES Institute of Technology, an AKTU-affiliated college. If you own the copyright and want it removed, email learnwithskillnest@gmail.com and we will take it down.