Question 21 : Having multiple perceptrons can actually solve the XOR problem satisfactorily: this is because each perceptron can partition off a linear part of the space itself, and they can then combine their results
1. True – this works always, and these multiple perceptrons learn to classify even complex problems
2. False – perceptrons are mathematically incapable of solving linearly inseparable functions, no matter what you do
3. True – perceptrons can do this but are unable to learn to do it – they have to be explicitly hand-coded
4. False – just having a single perceptron is enough
View Answer   Discuss with Members

Question 22 : The name for the function in question 16 is
1. Step function
2. Heaviside function
3. Logistic function
4. Perceptron function
View Answer   Discuss with Members

Question 23 : Neural Networks are complex ______________ with many parameters.
1. Linear Functions
2. Nonlinear Functions
3. Discrete Functions
4. Exponential Functions
View Answer   Discuss with Members

Question 24 : Which of the following is not the promise of artificial neural network?
1. It can explain result
2. It can survive the failure of some nodes
3. It has inherent parallelism
4. It can handle noise
View Answer   Discuss with Members

Question 25 : Why are linearly separable problems of interest of neural network researchers?
1. Because they are the only class of problem that network can solve successfully
2. Because they are the only class of problem that Perceptron can solve successfully
3. Because they are the only mathematical functions that are continue
4. Because they are the only mathematical functions you can draw
View Answer   Discuss with Members

Question 26 : What is back propagation?
1. It is another name given to the curvy function in the perceptron
2. It is the transmission of error back through the network to adjust the inputs
3. It is the transmission of error back through the network to allow weights to be adjusted so that the network can learn
4. None of the mentioned
View Answer   Discuss with Members

Question 27 : Why is the XOR problem exceptionally interesting to neural network researchers?
1. Because it can be expressed in a way that allows you to use a neural network
2. Because it is complex binary operation that cannot be solved using neural networks
3. Because it can be solved by a single layer perceptron
4. Because it is the simplest linearly inseparable problem that exists.
View Answer   Discuss with Members

Question 28 : Neuro software is:
1. A software used to analyze neurons
2. It is powerful and easy neural network
3. Designed to aid experts in real world
4. It is software used by Neurosurgeon
View Answer   Discuss with Members

Question 29 : Which of the following is true?
(i) On average, neural networks have higher computational rates than conventional computers.
(ii) Neural networks learn by example.
(iii) Neural networks mimic the way the human brain works.
1. All of the mentioned are true
2. (ii) and (iii) are true
3. (i), (ii) and (iii) are true
4. None of the mentioned
View Answer   Discuss with Members

Question 30 : A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2. The inputs are 4, 10, 5 and 20 respectively. The output will be:
1. 238
2. 76
3. 119
4. 123
View Answer   Discuss with Members