Scribd
Upload
224 views1 page

Question Bank Module 1

This document contains 15 questions about neural networks and machine learning algorithms. The questions cover topics such as the mathematical models of the perceptron and multilayer perceptron neurons, comparing perceptrons and multilayer perceptrons, learning algorithms like the perceptron learning algorithm, convergence properties of perceptrons, and using perceptrons to learn different functions like OR, AND, XOR.

Uploaded by

Raushan Kashyap
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
224 views1 page

Question Bank Module 1

This document contains 15 questions about neural networks and machine learning algorithms. The questions cover topics such as the mathematical models of the perceptron and multilayer perceptron neurons, comparing perceptrons and multilayer perceptrons, learning algorithms like the perceptron learning algorithm, convergence properties of perceptrons, and using perceptrons to learn different functions like OR, AND, XOR.

Uploaded by

Raushan Kashyap
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

Question Bank on First Module I (Partial)

Q1: Explain MP Neuron. Give its mathematical model.

Q2:- Explain achievements of MP Neuron and write about its limitation.

Q3:- Explain basic Perceptron. Give its Mathematical Model.

Q4:- Compare Perceptron with MP Neuron.

Q5:- Show mathematically that Perceptron can learn OR/AND function.

Q6:- Show mathematically that single Perceptron is not able to learn X-OR/X-NOR function.

Q7:- Explain Perceptron learning algorithm.

Q8:- With what type of data set the Perceptron will final converge and will never converge.

Q9:- How can you be sure that Perceptron algorithm has finally converged.

Q10:- Suppose the initial weight vector W= [0 1 0 0]. What will be the final value of weight vector, after convergence for

OR function, if the points are selected in following order repeatedly.

000, 001, 010, 011, 100, 101, 110, 111.

Q11:- Can Perceptron learning algorithm work on real valued data set. If yes show how? If No, Why not?

Q12:- Show that two layers of Perceptron can learn X-OR/X-NOR function.

Q13:- Argue that two layers of Perceptron can learn any function of any dimensionality.

Q14:- Intuitively argue, what happens when layers of Perceptron are used to separate initially non separable data by

linear functions?

Q15:- What is sigmoid function and explain, why to go for Sigmoid Neuron.

You might also like