Which of the following is true about Batchnorm?

When should multi-task learning be used?

What is Error Analysis?

Which of the following is a non-iterative method to generate adversarial examples?

Which, if any, of the following propositions is true about fully-connected neural networks (FCNN)?

How many layers Deep learning algorithms are constructed?

In CNN, having max pooling always decrease the parameters?

Which of the following is NOT the CNN layers?

Which of the following is/are Common uses of RNNs?

Which of the following is well suited for perceptual tasks?

CNN is mostly used when there is an?

Which neural network has only one hidden layer between the input and output?

The number of nodes in the input layer is 10 and the hidden layer is 5. The maximum number of connections from the input layer to the hidden layer are

Deep learning algorithms are _______ more accurate than machine learning algorithm in image classification

In which of the following applications can we use deep learning to solve the problem?

Which of the following statements is true when you use 1×1 convolutions in a CNN?

Which of the following methods DOES NOT prevent a model from overfitting to the training set?

The input image has been converted into a matrix of size 28 X 28 and a kernel/filter of size 7 X 7 with a stride of 1. What will be the size of the convoluted matrix?

In a simple MLP model with 8 neurons in the input layer, 5 neurons in the hidden layer and 1 neuron in the output layer. What is the size of the weight matrices between hidden output layer and input hidden layer?

Which of the following functions can be used as an activation function in the output layer if we wish to predict the probabilities of n classes (p1, p2..pk) such that sum of p over all n equals to 1?

Assume a simple MLP model with 3 neurons and inputs= 1,2,3. The weights to the input neurons are 4,5 and 6 respectively. Assume the activation function is a linear constant value of 3. What will be the output ?

Which of the following would have a constant input in each epoch of training a Deep Learning model?

Sentiment analysis using Deep Learning is a many-to one prediction task

RNNs stands for?

Output of sigmoid function has the range from:

Output of tanh function has the range from:

The Deep Learning first layer is called the?

LSTM stands for?

Assume that your machine has a large enough RAM dedicated to training neural networks. Compared to using stochastic gradient descent for your optimization, choosing a batch size that fits your RAM will lead to:

Which of the following methods DOES NOT prevent a model from overfitting to the training set?

What is back propagation?

Supervised learning and unsupervised clustering both require at least one

Supervised learning differs from unsupervised clustering in that supervised learning requires

Another name for an output attribute

Assume that we have a dataset containing information about 200 individuals. One hundred of these individuals have purchased life insurance. A supervised data mining session has discovered the following rule:

IF age < 30 & credit card insurance = yes THEN life insurance = yes

Rule Accuracy: 70%

Rule Coverage: 63%

How many individuals in the class life insurance= no have credit card insurance and

are less than 30 years old?

Which statement is true about neural network and linear regression models?

Unlike traditional production rules, association rules

. Which of the following is a common use of unsupervised clustering?

The average positive difference between computed and desired outcome values

Given desired class Cand population P, lift is defined as

Deep learning works well despite of problem(s).

An average human brain has around neurons(aprox)

Which of the following statements is true for the Perceptron Learning Algorithm?

Statement I: Threshold needs to be hand coded

Statement II: Threshold can be learnt

Which kind of optimisation is required in 2-class linear SVM training procedure?

The distance of a feature vector [2, 3, -2] from separating plane x1+2x2+2x3+5=0 is given

by

For the separable data with D-dimensional feature vectors, K classes and a total of N examples, how many unknown variables are to be estimated in SVM training to get a separating plane 'which maximizes margin? How many constraints?

The values of Lagrange multipliers corresponding to the support vectors can be:

A data point with 5 dimensions [27,40, -15,30,38] obtain a score [18, 20, -5, -15,19].

Find the Hinge loss incurred by second class (class 2) with a margin of 5 is given by:

One form of sigmoid function logistic function

In sigmoid (logistic) function when WTX=0, then sigmoid value is equal to

In logistic function, when we increase the value of „w‟, the function becomes

Which parameter(s) need to be learnt in minimizing objective function in supervised learning?

Why convolution neural network is taking off quickly in recent times

Momentum based gradient descent algorithm and Nesterov accelerated gradient descent are faster

than Stochastic gradient descent algorithm

Consider the following statement, “It takes less time to navigate the regions having a gentle slope”

The above statement is true in case of

I. Gradient descent algorithm

II. Momentum based gradient descent algorithm

Identify the technique that is used to achieve relatively better learning rate by updating w using

bunch of different values of η.

There is no guarantee that the loss decreases at each step in a stochastic Gradient Descent”

Identify the advantages of Nesterov accelerated gradient descent.

I. Corrects its course quicker than Momentum-based gradient descent

II. Oscillations are smaller

III. Chances of escaping minima valley are also smaller

Pick out the methods for annealing learning rate that has only number of epochs as the hyperparameter

Adagrad got stuck when it was close to convergence. How does RMSProp overcome this problem?

Which of the following gradient descent algorithm suffers from more oscillations?

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?

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

..“Convolutional Neural Networks can perform various types of transformation (rotations or

scaling) in an input”. Is the statement correct True or False?

Which of the following techniques perform similar operations as dropout in a neural network?

Which of the following gives non-linearity to a neural network?

If you increase the number of hidden layers in a Multi Layer Perceptron, the classification error of

test data always decreases. True or False?

Which of the following is true about model capacity (where model capacity means the ability of

neural network to approximate complex functions) ?

If you increase the number of hidden layers in a Multi Layer Perceptron, the classification error of

test data always decreases. True or False?

Can a neural network model the function (y=1/x)?

In which neural net architecture, does weight sharing occur?

Batch Normalization is helpful because

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?

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?

What is the purpose of Gradient Descent algorithm?

Which is true for neural networks?

What is a dead unit in a neural network?

Which of the following statement is the best description of early stopping?

What if we use a learning rate that’s too large?

Which gradient technique is more advantageous when the data is too big to handle in RAM simultaneously?

What are the factors to select the depth of neural network?

1. Type of neural network (eg. MLP, CNN etc)

2. Input data

3. Computation power, i.e. Hardware capabilities and software capabilities

4. Learning Rate

5. The output function to map

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?

Increase in size of a convolutional kernel would necessarily increase the performance of a

convolutional network

Which kind of activation function is typical for a convolution layer in an RNN

Which of the following method use arithmetic operation in evaluation of word representation?

Which of the following model directly learn word representations?

Which of the following is correct in word representation model?

I. In continuous bag of word model, the softmax function is computationally

expensive.

II. In continuous bag of word model, the softmax function is computationally

inexpensive.

III. In Skip-gram model, the softmax function is computationally inexpensive.

IV. In Skip-gram model, the softmax function is computationally expensive

Which of the following solution constructs a binary tree in learning word representation using prediction- based models?

Which of the following method(s) use dot product in the evaluation of word representation?

I. Semantic relatedness

II. Synonym detection

III. Semantic analogy

If you need to design a model for textual entailment from the text, then which of the following steps will you choose?

I. CNN is used to encode the text

II. CNN is used to decode the text

III. RNN is used to decode the text from the encoding

IV. RNN is used to encode the text.

V. RNN is used to encode the text and decode the text.

The problem of generating the sentence given an image can be possibly solved with the encoder decoder architecture

For document classification and summarization, it is important to look at the important sentences

and important words. What kind of “attention” mechanism is required for encoding?

48 filters of size 21 x 21 is applied to an image of size 327 x 327, with zero padding and stride of 3. The image is an RGB image. The depth of the filter is same as the depth of image. What will be the volume of the final image?

While reconstructing images from embeddings, if we consider deeper layers of the network, how is the image affected?

Which of the following is true for content and style of image w.r.t. Deep Art?

It is very easy to fool a CNN. Which of the following statements doesn‟t support the above argument?

Which of the following includes major tasks of NLP?

Which of the following is used to mapping sentence plan into sentence structure?

Given a sound clip of a person or people speaking, determine the textual representation of the speech