Question bank soft computing
Download as DOC, PDF2 likes3,210 views
This document contains 40 questions about soft computing concepts including neural networks, fuzzy systems, evolutionary computation, and hybrid intelligent systems. The questions cover topics such as the differences between hard and soft computing, components of expert systems, applications of artificial neural networks, types of learning in neural networks, perceptrons, adaptive linear neurons, backpropagation networks, and training algorithms for various neural network architectures.
![33. Construct a Maxnet with four neurons and inhibitory weight ɛ = 0.2, Given the initial
activations (input signals) as follows:
A1(0)=0.3 , A2(0)=0.5 , A3(0)=0.7, A4(0)=0.9
34. Construct a Maxnet with four neurons and inhibitory weight ɛ = 0.2, Given the initial
activations (input signals) as follows:
A1(0)=0.4 , A2(0)=0.5 , A3(0)=0.6, A4(0)=0.8
35. Implement AND function using perceptron networks for bipolar inputs and targets.
36. Implement OR function using perceptron networks for bipolar inputs and targets.
37. Implement ANDNOT function when all the inputs are presented only one time. Use
bipolar inputs and targets.
38. Implement OR function with bipolar inputs and targets using Adaline network.
39. Using Madaline network, implement XOR functio targets. Assume the required
parameters for training of the network (Fig D).
40. Using back-propagation network, find the new weights for the net shown in figure. It is
presented with the input pattern [0,1] and the target output is 1. Use a learning rate α
=0.25 and binary sigmoidal activation function (Fig E).](https://image.slidesharecdn.com/questionbank-softcomputing-160926063951/85/Question-bank-soft-computing-3-320.jpg)
Question bank soft computing
- 1. Question Bank : Introduction to Soft Computing – NOE 031 Unit 1 & 2 1. What is Soft Computing? 2. Differentiate between Hard Computing and Soft Computing. 3. What is an expert system? Explain in brief components of expert system. What are the applications of expert system? 4. Explain in brief application areas of Soft computing? 5. List the applications of Soft computing. 6. What is ANN? List the characteristics of ANN. 7. Compare Biological neural network and Artificial neural network. 8. Explain in brief basic models of Artificial Neural Network. 9. What is learning? What are different types of learning? 10. Write a short note on a. Supervised learning b. Unsupervised learning c. Reinforcement learning d. Activation function e. Perceptron network f. Adaptive Linear Neuron (Adaline) g. Multiple Adaptive Linear Neuron (Madaline) 11. What is supervised learning and how it is different from unsupervised learning? 12. What is the building block of the perceptron? Does perceptron require supervised learning? If no, What does it require? 13. List the limitations of perceptron and applications of perceptron network. 14. List the stages involved in training of back propagation network. 15. What is local minima and global minima?
- 2. 16. Write an algorithm for training perceptron network. 17. Write an algorithm for training Adaptive Linear Neuron (Adaline) 18. Write an algorithm for training Multiple Adaptive Linear Neuron (Madaline) 19. What do you understand by back propagation network? Explain in brief its architecture. 20. Explain in brief error back propagation algorithm. 21. What are the applications of BPN? 22. What are the factors that improve the convergence of learning in BPN network? 23. What is the necessity of momentum factor in weight updation process? 24. What is content addressable memory? 25. What is the functional difference between a RAM and a CAM 26. Explain the Hebb rule training algorithm used in pattern association 27. List the fixed weight competitive nets. Explain one 28. List the special neural networks for typical applications. 29. What is the principle behind simulated annealing network? Explain SAN in brief. 30. For the network shown in figure, calculate the net input to the output neuron (Fig A) 31. Calculate the net input for the network shown in figure with bias included in the network (Fig B) 32. Obtain the output of the neuron Y for the network shown in figure C using activation functions as: a. binary sigmoidal and b. bipolar sigmoidal
- 3. 33. Construct a Maxnet with four neurons and inhibitory weight ɛ = 0.2, Given the initial activations (input signals) as follows: A1(0)=0.3 , A2(0)=0.5 , A3(0)=0.7, A4(0)=0.9 34. Construct a Maxnet with four neurons and inhibitory weight ɛ = 0.2, Given the initial activations (input signals) as follows: A1(0)=0.4 , A2(0)=0.5 , A3(0)=0.6, A4(0)=0.8 35. Implement AND function using perceptron networks for bipolar inputs and targets. 36. Implement OR function using perceptron networks for bipolar inputs and targets. 37. Implement ANDNOT function when all the inputs are presented only one time. Use bipolar inputs and targets. 38. Implement OR function with bipolar inputs and targets using Adaline network. 39. Using Madaline network, implement XOR functio targets. Assume the required parameters for training of the network (Fig D). 40. Using back-propagation network, find the new weights for the net shown in figure. It is presented with the input pattern [0,1] and the target output is 1. Use a learning rate α =0.25 and binary sigmoidal activation function (Fig E).