Deep Learning
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.
Which of the following statement(s) correctly represents a real neuron?
A. A neuron has a single input and a single output only
B. A neuron has multiple inputs but a single output only
C. A neuron has a single input but multiple outputs
D. A neuron has multiple inputs and multiple outputs
E. All of the above statements are valid
Solution: (E)
A neuron can have a single Input / Output or multiple Inputs / Outputs.
Q2. Below is a mathematical representation of a neuron.
The different components of the neuron are denoted as:
- 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
Solution: (A)
A single neuron with no non-linearity can be considered as a linear regression function.
Q3. Let us assume we implement an AND function to a single neuron. Below is a tabular representation of an AND function:
X1 | X2 | X1 AND X2 |
0 | 0 | 0 |
0 | 1 | 0 |
1 | 0 | 0 |
1 | 1 | 1 |
The activation function of our neuron is denoted as:
What would be the weights and bias?
(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
Solution: (A)
A.
- 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
Therefore option A is correct
Q4. A network is created when we multiple neurons stack together. Let us take an example of a neural network simulating an XNOR function.
You can see that the last neuron takes input from two neurons before it. The activation function for all the neurons is given by:
Suppose X1 is 0 and X2 is 1, what will be the output for the above neural network?
A. 0
B. 1
Solution: (A)
Output of a1: f(0.5*1 + -1*0 + -1*1) = f(-0.5) = 0
Output of a2: f(-1.5*1 + 1*0 + 1*1) = f(-0.5) = 0
Output of a3: f(-0.5*1 + 1*0 + 1*0) = f(-0.5) = 0
So the correct answer is 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?
A. Assign random values and pray to God they are correct
B. Search every possible combination of weights and biases till you get the best value
C. Iteratively check that after assigning a value how far you are from the best values, and slightly change the assigned values values to make them better
D. None of these
Solution: (C)
Option C is the description of gradient descent.
Q6. What are the steps for using a gradient descent algorithm?
- Calculate error between the actual value and the predicted value
- Reiterate until you find the best weights of network
- Pass an input through the network and get values from output layer
- Initialize random weight and bias
- 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
Solution: (D)
Option D is correct
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 + y
f = q * z
Graphical representation of the functions is as follows:
What is the gradient of F with respect to x, y, and 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)
Solution: (C)
Option C is correct.
Q8. Now let’s revise the previous slides. We have learned that:
- A neural network is a (crude) mathematical representation of a brain, which consists of smaller components called neurons.
- Each neuron has an input, a processing function, and an output.
- These neurons are stacked together to form a network, which can be used to approximate any function.
- To get the best possible neural network, we can use techniques like gradient descent to update our neural network model.
Given above is a description of a neural network. When does a neural network model become a deep learning model?
A. When you add more hidden layers and increase depth of neural network
B. When there is higher dimensionality of data
C. When the problem is an image recognition problem
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.
Q9. A neural network can be considered as multiple simple equations stacked together. Suppose we want to replicate the function for the below mentioned decision boundary.
Using two simple inputs h1 and h2
What will be the final equation?
A. (h1 AND NOT h2) OR (NOT h1 AND h2)
B. (h1 OR NOT h2) AND (NOT h1 OR h2)
C. (h1 AND h2) OR (h1 OR h2)
D. None of these
Solution: (A)
As you can see, combining h1 and h2 in an intelligent way can get you a complex equation easily. Refer Chapter 9 of this book
Q10. “Convolutional Neural Networks can perform various types of transformation (rotations or scaling) in an input”. Is the statement correct True or False?
A. True
B. False
Solution: (B)
Data Preprocessing steps (viz rotation, scaling) is necessary before you give the data to neural network because neural network cannot do it itself.
Q11. Which of the following techniques perform similar operations as dropout in a neural network?
A. Bagging
B. Boosting
C. Stacking
D. None of these
Solution: (A)
Q 12. Which of the following gives non-linearity to a neural network?
A. Stochastic Gradient Descent
B. Rectified Linear Unit
C. Convolution function
D. None of the above
Solution: (B)
Rectified Linear unit is a non-linear activation function.
Q13. In training a neural network, you notice that the loss does not decrease in the few starting epochs.
The reasons for this could be:
- The learning is rate is low
- Regularization parameter is high
- Stuck at local minima
What according to you are the probable reasons?
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) ?
A. As number of hidden layers increase, model capacity increases
B. As dropout ratio increases, model capacity increases
C. As learning rate increases, model capacity increases
D. None of these
Solution: (A)
Only option A is correct.
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
Solution: (B)
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.
Which of the following architecture has feedback connections?
A. Recurrent Neural network
B. Convolutional Neural Network
C. Restricted Boltzmann Machine
D. None of these
Solution: (A)
Option A is correct.
Q17. What is the sequence of the following tasks in a perceptron?
- Initialize weights of perceptron randomly
- Go to the next batch of dataset
- If the prediction does not match the output, change the weights
- For a sample input, compute an output
A. 1, 2, 3, 4
B. 4, 3, 2, 1
C. 3, 1, 2, 4
D. 1, 4, 3, 2
Solution: (D)
Sequence D is correct.
Q18. Suppose that you have to minimize the cost function by changing the parameters. Which of the following technique could be used for this?
A. Exhaustive Search
B. Random Search
C. Bayesian Optimization
D. Any of these
Solution: (D)
Any of the above mentioned technique can be used to change parameters.
Q19. First Order Gradient descent would not work correctly (i.e. may get stuck) in which of the following graphs?
A.
B.
C.
D. None of these
Solution: (B)
This is a classic example of saddle point problem of gradient descent.
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).
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.
What could be the possible reason for this decrease?
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
Solution: (C)
As mentioned in option C, the possible reason could be kernel correlation.
Q21. Suppose we have one hidden layer neural network as shown above. The hidden layer in this network works as a dimensionality reductor. Now instead of using this hidden layer, we replace it with a dimensionality reduction technique such as PCA.
Would the network that uses a dimensionality reduction technique always give same output as network with hidden layer?
A. Yes
B. No
Solution: (B)
Because PCA works on correlated features, whereas hidden layers work on predictive capacity of features.
Q22. Can a neural network model the function (y=1/x)?
A. Yes
B. No
Solution: (A)
Option A is true, because activation function can be reciprocal function.
Q23. In which neural net architecture, does weight sharing occur?
A. Convolutional neural Network
B. Recurrent Neural Network
C. Fully Connected Neural Network
D. Both A and B
Solution: (D)
Option D is correct.
Q24. Batch Normalization is helpful because
A. It normalizes (changes) all the input before sending it to the next layer
B. It returns back the normalized mean and standard deviation of weights
C. It is a very efficient backpropagation technique
D. None of these
Solution: (A)
To read more about batch normalization, see refer this video
Q25. Instead of trying to achieve absolute zero error, we set a metric called bayes error which is the error we hope to achieve. What could be the reason for using bayes error?
A. Input variables may not contain complete information about the output variable
B. System (that creates input-output mapping) may be stochastic
C. Limited training data
D. All the above
Solution: (D)
In reality achieving accurate prediction is a myth. So we should hope to achieve an “achievable result”.
Q26. The number of neurons in the output layer should match the number of classes (Where the number of classes is greater than 2) in a supervised learning task. True or False?
A. True
B. False
Solution: (B)
It depends on output encoding. If it is one-hot encoding, then its true. But you can have two outputs for four classes, and take the binary values as four classes(00,01,10,11).
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
Solution: (D)
All of the techniques can be used to deal with overfitting.
Q28. Y = ax^2 + bx + c (polynomial equation of degree 2)
Can this equation be represented by a neural network of single hidden layer with linear threshold?
A. Yes
B. No
Solution: (B)
The answer is no because having a linear threshold restricts your neural network and in simple terms, makes it a consequential linear transformation function.
Q29. What is a dead unit in a neural network?
A. A unit which doesn’t update during training by any of its neighbour
B. A unit which does not respond completely to any of the training patterns
C. The unit which produces the biggest sum-squared error
D. None of these
Solution: (A)
Option A is correct.
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
D. A faster version of backpropagation, such as the `Quickprop’ algorithm
Solution: (B)
Option B is correct.
Q31. What if we use a learning rate that’s too large?
A. Network will converge
B. Network will not converge
C. Can’t Say
Solution: B
Option B is correct because the error rate would become erratic and explode.
Q32. The network shown in Figure 1 is trained to recognize the characters H and T as shown below:
What would be the output of the network?
- Could be A or B depending on the weights of neural network
Solution: (D)
Without knowing what are the weights and biases of a neural network, we cannot comment on what output it would give.
Q33. Suppose a convolutional neural network is trained on ImageNet dataset (Object recognition dataset). This trained model is then given a completely white image as an input.The output probabilities for this input would be equal for all classes. True or False?
A. True
B. False
Solution: (B)
There would be some neurons which are do not activate for white pixels as input. So the classes wont be equal.
Q34. When pooling layer is added in a convolutional neural network, translation in-variance is preserved. True or False?
A. True
B. False
Solution: (A)
Translation invariance is induced when you use pooling.
Q35. Which gradient technique is more advantageous when the data is too big to handle in RAM simultaneously?
A. Full Batch Gradient Descent
B. Stochastic Gradient Descent
Solution: (B)
Option B is correct.
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.
Which of the following statements is true?
A. Hidden layer 1 corresponds to D, Hidden layer 2 corresponds to C, Hidden layer 3 corresponds to B and Hidden layer 4 corresponds to A
B. Hidden layer 1 corresponds to A, Hidden layer 2 corresponds to B, Hidden layer 3 corresponds to C and Hidden layer 4 corresponds to D
Solution: (A)
This is a description of a vanishing gradient problem. As the backprop algorithm goes to starting layers, learning decreases.
Q37. For a classification task, instead of random weight initializations in a neural network, we set all the weights to zero. Which of the following statements is true?
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
Solution: (B)
Option B is correct.
Q38. There is a plateau at the start. This is happening because the neural network gets stuck at local minima before going on to global minima.
To avoid this, which of the following strategy should work?
A. Increase the number of parameters, as the network would not get stuck at local minima
B. Decrease the learning rate by 10 times at the start and then use momentum
C. Jitter the learning rate, i.e. change the learning rate for a few epochs
D. None of these
Solution: (C)
Option C can be used to take a neural network out of local minima in which it is stuck.
Q39. For an image recognition problem (recognizing a cat in a photo), which architecture of neural network would be better suited to solve the problem?
A. Multi Layer Perceptron
B. Convolutional Neural Network
C. Recurrent Neural network
D. Perceptron
Solution: (B)
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
Q40. Suppose while training, you encounter this issue. The error suddenly increases after a couple of iterations.
You determine that there must a problem with the data. You plot the data and find the insight that, original data is somewhat skewed and that may be causing the problem.
What will you do to deal with this challenge?
A. Normalize
B. Apply PCA and then Normalize
C. Take Log Transform of the data
D. None of these
Solution: (B)
First you would remove the correlations of the data and then zero center it.
Q41. Which of the following is a decision boundary of Neural Network?
A) B
B) A
C) D
D) C
E) All of these
Solution: (E)
A neural network is said to be a universal function approximator, so it can theoretically represent any decision boundary.
Q42. In the graph below, we observe that the error has many “ups and downs”
Should we be worried?
A. Yes, because this means there is a problem with the learning rate of neural network.
B. No, as long as there is a cumulative decrease in both training and validation error, we don’t need to worry.
Solution: (B)
Option B is correct. In order to decrease these “ups and downs” try to increase the batch size.
Q43. What are the factors to select the depth of neural network?
- Type of neural network (eg. MLP, CNN etc)
- Input data
- Computation power, i.e. Hardware capabilities and software capabilities
- Learning Rate
- The output function to map
A. 1, 2, 4, 5
B. 2, 3, 4, 5
C. 1, 3, 4, 5
D. All of these
Solution: (D)
All of the above factors are important to select the depth of neural network
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?
A. Re-train the model for the new dataset
B. Assess on every layer how the model performs and only select a few of them
C. Fine tune the last couple of layers only
D. Freeze all the layers except the last, re-train the last layer
Solution: (D)
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.
Q45. Increase in size of a convolutional kernel would necessarily increase the performance of a convolutional network.
A. True
B. False
Solution: (B)
Increasing kernel size would not necessarily increase performance. This depends heavily on the dataset.
Comments
Post a Comment