Professional Documents
Culture Documents
4 MCQ Ann Ann Quiz Selected
4 MCQ Ann Ann Quiz Selected
Ans : B
Explanation: The inventor of the first neurocomputer, Dr. Robert Hecht-Nielsen.
Answer: Explanation:
There are two Artificial Neural Network topologies : FeedForward and Feedback.
So, option A is correct.
Answer : C
Explanation: In FeedBack ANN, loops are allowed. They are used in content addressable
memories. So, option C is correct.
5. What is the name of node which take binary values TRUE (T) and FALSE (F)?
A. Dual Node
B. Binary Node
C. Two-way Node
D. Ordered Node
Ans : B
Explanation: Boolean nodes : They represent propositions, taking binary values TRUE (T) and
lOMoARcPSD|18922087
FALSE (F).
6. Neural Networks are complex with many parameters.
A. Linear Functions
B. Nonlinear Functions
C. Discrete Functions
D. Exponential Functions
Ans : A
Explanation: Neural networks are complex linear functions with many parameters.
Ans : A
Explanation: The artificial Neural Network (ANN) cannot explain result.
Ans: A
Explanation: The output at each node is called its activation or node value.
Ans : C
Explanation: Artificial Neural Networks is the full form of ANNs.
Ans : A
Explanation: FeedForward ANN the information flow is unidirectional
D. Supervised Learning
Ans : C
Explanation: Supreme Learning is not an Machine Learning strategies in ANNs.
Ans : D
Explanation: All above are appliction of Neural Networks.
Ans : A
Explanation: The perceptron is a single layer feed-forward neural network.
14. 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, 3, 2 and 1 respectively. What
will be the output?
A. 30
B. 40
C. 50
D. 60
Ans : B
Explanation: The output is found by multiplying the weights with their respective inputs,
summing the results and multiplying with the transfer function. Therefore: Output = 2 * (1*4 +
2*3 + 3*2 + 4*1) = 40.
Ans : C
Explanation: Back propagation is the transmission of error back through the network to allow
weights to be adjusted so that the network can learn.
16. The network that involves backward links from output to the input and hidden
layers is called
lOMoARcPSD|18922087
Ans : C
Explanation: RNN (Recurrent neural network) topology involves backward links from output
to the input and hidden layers.
Answer : D
Explanation: Artificial neural network is used for: Classification, Clustering and Pattern
recognition all of the above.
Q1. A neural network model is said to be inspired from the human brain.
The neural network consists of many neurons, each neuron takes an input,
processes it and gives an output. Here’s a diagrammatic representation of a real
neuron.
lOMoARcPSD|18922087
Answer: A neuron can have a single Input / Output or multiple Inputs / Outputs.
x1, x2,…, xN: These are inputs to the neuron. These can either be the actual
observations from input layer or an intermediate value from one of the hidden
layers.
w1, w2,…,wN: The Weight of each input.
bi: Is termed as Bias units. These are constant values added to the input of the
activation function corresponding to each weight. It works similar to an intercept
term.
a: Is termed as the activation of the neuron which can be represented as
and y: is the output of the neuron
Considering the above notations, will a line equation (y = mx + c) fall into the category of
a neuron?
A. Yes
B. No
X1 X2 X1 AND X2
0 0 0
0 1 0
1 0 0
1 1 1
(Hint: For which values of w1, w2 and b does our neuron implement an AND function?)
A. Bias = -1.5, w1 = 1, w2 = 1
B. Bias = 1.5, w1 = 2, w2 = 2
C. Bias = 1, w1 = 1.5, w2 = 1.5
D. None of these
Answer:
f(-1.5*1 + 1*0 + 1*0) = f(-1.5) = 0
f(-1.5*1 + 1*0 + 1*1) = f(-0.5) = 0
f(-1.5*1 + 1*1 + 1*0) = f(-0.5) = 0
f(-1.5*1 + 1*1+ 1*1) = f(0.5) = 1
Q4. A network is created when we multiple neurons stack together. Let us take an
Suppose X1 is 0 and X2 is 1, what will be the output for the above neural network?
A. 0
B. 1
Answer:
Solution: (A)
Q5. In a neural network, knowing the weight and bias of each neuron is the most
important step. If you can somehow get the correct value of weight and bias for each
neuron, you can approximate any function. What would be the best way to approach this?
Solution: (C)
Option C is the description of gradient descent.
lOMoARcPSD|18922087
Q6. What are the steps for using a gradient descent algorithm?
1. Calculate error between the actual value and the predicted value
2. Reiterate until you find the best weights of network
3. Pass an input through the network and get values from output layer
4. Initialize random weight and bias
5. Go to each neurons which contributes to the error and change its respective
values to reduce the error
A. 1, 2, 3, 4, 5
B. 5, 4, 3, 2, 1
C. 3, 2, 1, 5, 4
D. 4, 3, 1, 5, 2
Q7. Suppose you have inputs as x, y, and z with values -2, 5, and -4 respectively.
You have a neuron ‘q’ and neuron ‘f’ with functions:
q=x+yf=q*z
(HINT: To calculate gradient, you must find (df/dx), (df/dy) and (df/dz))
A. (-3,4,4)
B. (4,4,3)
C. (-4,-4,3)
D. (3,-4,-4)
lOMoARcPSD|18922087
Q8. Now let’s revise the previous slides. We have learned that:
A. When you add more hidden layers and increase depth of neural network
D. None of these
Solution: (A)
More depth means the network is deeper. There is no strict rule of how many layers are
necessary to make a model deep, but still if there are more than 2 hidden layers, the model is
said to be deep.
Q13. In training a neural network, you notice that the loss does not decrease in the
few starting epochs.
A. 1 and 2
B. 2 and 3
C. 1 and 3
D. Any of these
Solution: (D)
The problem can occur due to any of the reasons mentioned.
Q14. Which of the following is true about model capacity (where model capacity means
the ability of neural network to approximate complex functions) ?
D. None of these
Q15. If you increase the number of hidden layers in a Multi Layer Perceptron, the
classification error of test data always decreases. True or False?
A. True
B. False
Answer: This is not always true. Overfitting may cause the error to increase.
Q16. You are building a neural network where it gets input from the previous layer as
well as from itself.
lOMoARcPSD|18922087
D. None of these
A. 1, 2, 3, 4
B. 4, 3, 2, 1
C. 3, 1, 2, 4
D. 1, 4, 3, 2
Q20. The below graph shows the accuracy of a trained 3-layer convolutional neural
network vs the number of parameters (i.e. number of feature kernels).
lOMoARcPSD|18922087
The trend suggests that as you increase the width of a neural network, the accuracy
increases till a certain threshold value, and then starts decreasing.
A. Even if number of kernels increase, only few of them are used for prediction
B. As the number of kernels increase, the predictive power of neural network decrease
C. As the number of kernels increase, they start to correlate with each other which in
turn helps overfitting
D. None of these
D. Both A and B
Q27. In a neural network, which of the following techniques is used to deal with
overfitting?
A. Dropout
B. Regularization
C. Batch Normalization
D. All of these
Can this equation be represented by a neural network of single hidden layer with linear
threshold?
A. Yes
B. No
lOMoARcPSD|18922087
Answer: The answer is no because having a linear threshold restricts your neural network and
in simple terms, makes it a consequential linear transformation function.
Q30. Which of the following statement is the best description of early stopping?
A. Train the network until a local minimum in the error function is reached
B. Simulate the network on a test dataset after every epoch of training. Stop training
when the generalization error starts to increase
C. Add a momentum term to the weight update in the Generalized Delta Rule, so that training
converges more quickly
Answer: Option B is correct because the error rate would become erratic and explode.
Q34. When pooling layer is added in a convolutional neural network, translation in-
variance is preserved. True or False?
A. True
B. False
Q36. The graph represents gradient flow of a four-hidden layer neural network which is
trained using sigmoid activation function per epoch of training. The neural network
suffers with the vanishing gradient problem.
lOMoARcPSD|18922087
Answer: This is a description of a vanishing gradient problem. As the backprop algorithm goes
to starting layers, learning decreases.
A. There will not be any problem and the neural network will train properly
B. The neural network will train but all the neurons will end up recognizing the same
thing
C. The neural network will not train as there is no net gradient change
D. None of these
Answer: Convolutional Neural Network would be better suited for image related problems
because of its inherent nature for taking into account changes in nearby locations of an image
Q43. What are the factors to select the depth of neural network?
A. 1, 2, 4, 5
B. 2, 3, 4, 5
C. 1, 3, 4, 5
D. All of these
Q44. Consider the scenario. The problem you are trying to solve has a small amount of
data. Fortunately, you have a pre-trained neural network that was trained on a similar
problem. Which of the following methodologies would you choose to make use of this
pre-trained network?
B. Assess on every layer how the model performs and only select a few of them
D. Freeze all the layers except the last, re-train the last layer
Answer: If the dataset is mostly similar, the best method would be to train only the last layer, as
previous all layers work as feature extractors.
A. All of these
B. (ii) and (iii) are true
C. (i), (ii) and (iii) are true
D. None of these
Answer: a
Explanation: Neural networks have higher computational rates than conventional computers
because a lot of the operation is done in parallel. That is not the case when the neural network is
simulated on a computer. The idea behind neural nets is based on the way the human brain
works. Neural nets cannot be programmed, they can only learn by example
A. All of these
B. (ii) is true
C. (i) and (ii) are true
D. None of these
Answer: c
Explanation: The training time depends on the size of the network; the number of neuron is
greater and therefore the number of possible ‘states’ is increased. Neural networks can be
simulated on a conventional computer but the main advantage of neural networks – parallel
execution – is lost. Artificial neurons are not identical in operation to the biological ones.
C. Only (i)
D. All of these
Answer:
Explanation: Neural networks learn by example. They are more fault tolerant because they are
always able to respond and small changes in input do not normally cause a change in output.
Because of their parallel architecture, high computational rates are achieved.
Answer: Pattern recognition is what single layer neural networks are best at but they don’t have
the ability to find the parity of a picture or to determine whether two shapes are connected or not.
A. Because it can be expressed in a way that allows you to use a neural network
B. Because it is complex binary operation that cannot be solved using neural networks
C. Because it can be solved by a single layer perceptron
D. Because it is the simplest linearly inseparable problem that exists.
A. Linear Functions
B. Nonlinear Functions
C. Discrete Functions
D. Exponential Functions
14.A perceptron adds up all the weighted inputs it receives, and if it exceeds a certain value,
it outputs a 1, otherwise it just outputs a 0.
A. True
B. False
C. Sometimes – it can also output intermediate values as well
D. Can’t say
lOMoARcPSD|18922087
A. Step function
B. Heaviside function
C. Logistic function
D. Perceptron function
Answer: Also known as the step function - so answer 1 is also right. It is a hard thresholding
function, either on or off with no in-between.
16. The network that involves backward links from output to the input and hidden
layers is called as .
Answer: Explanation: RNN (Recurrent neural network) topology involves backward links from
output to the input and hidden layers.
17. Which of the following is an application of NN (Neural Network)
A. Sales forecasting
B. Data validation
C. Risk management
D. All of these
A. Decision trees
B. Neural networks
C. Propositional and FOL rules
D. All of these
A. Supervised learning
B. Unsupervised learning
C. Active learning
D. Reinforcement learning
Answer: In automatic vehicle set of vision inputs and corresponding actions are available
to learner hence it’s an example of supervised learning.