You are on page 1of 3

Suez Canal University

Faculty of Computer and Information


Computer science Dept.

Sheet-6 Neural Networks

Answer The following questions: -

Q1: 1. What will be the values of net input of h1 and net input of h2 from
the below figure, given that w1 = 0.2, w2 = 0.15, w3 = 0.3, w4 = 0.25, w5 =
0.45, w6 =0.4, w7 = 0.55, w8 = 0.5?

a. 0.385, 0.378
b. 0.358, 0.682
c.0.853, 0.387
d. 0.583, 0.826

2-Explain the difference between Perceptron Learning and


Backpropagation.

3-When training a Neural Network by Backpropagation, what happens


if the Learning Rate is too low? What happens if it is too high?

4- In the artificial neural network, backward propagation delivers the:


a. Error value
b. Predicted value.
c. Unpredicted value.
d. Fixed value

5-What do you mean by backpropagation ______________ in neural


networks?
a. Forward pass of data
Suez Canal University
Faculty of Computer and Information
Computer science Dept.

b. Training process for adjusting weights


c. Activation of output layer
d. None of the above

6-In a feedforward neural network, information flows ___________.


a. Only in the forward direction
b. Only in the backward direction
c. In both forward and backward directions
d. In random directions
7-Which neural network layout is best for tasks involving image
classification?
a. Recurrent Neural Network (RNN)
b. Multilayer Perceptron (MLP)
c. Convolutional Neural Network (CNN)
d. Radial Basis Function Network (RBFN)

8-Which training method tries to reduce the discrepancy between expected


and actual results?
a. Gradient Descent
b. K-means clustering
c. Principal Component Analysis (PCa.)
d. None of the above

9-What is the basic building block of a neural network?


a. Neuron
b. Node
c. Weight
d. Layer

10-What are the main similarities and differences between feed–forward


neural networks and self–organising maps

11-What kind of learning is involved in pattern clustering task?


a. supervised
b. unsupervised
c. learning with critic
d. none of the mentioned
12-How are weights updated in feature maps?
a. updated for winning unit only
b. updated for neighbours of winner only
c. updated for winning unit and its neighbours
d. none of the mentioned

13- In self organizing network, how is layer connected to output layer?


a. some are connected
Suez Canal University
Faculty of Computer and Information
Computer science Dept.

b. all are one to one connected


c. each input unit is connected to each output unit
d. none of the mentioned

14-In competitive network, winning neuron has an output of


a.1
b.2
c. 0
d. none of the mentioned

15- Hamming Network is one of the simplest examples of


a. Competitive network
b. Hopfield network
c. none of the mentioned

16- Hamming network consists of


a.One layer
b.Two layer
c. Three layers

17- Competitive transfer function assigns an output------to the neuron


whose weight Closest to input vector
a. 1
b. 0
c. none of the mentioned

You might also like