NEW
Font size
WorksheetsDeep Learning
Total questions: 52
Worksheet time: 37mins
Which of the following is NOT supervised learning?
Decision Tree
Linear Regression
Naive Bayes
Clustering
What is the primary purpose of Back Propagation Networks (BPN)?
a) Image classification
b) Language translation
c) Minimizing error in neural networks
d) Generating random numbers
What is the basic building block of a neural network?
Layer
Neuron
Weight
Edge
What is the main goal of deep learning?
Unsupervised learning
Feature extraction
Training neural networks to learn from data and make predictions
Reinforcement learning
What does the term "ReLU" stand for in the context of activation functions?
Random Element Linear Unit
Resilient Learning Encoder
Recursive Leverage Engine
Rectified Linear Unit
Who am I? I am the most fundamental block of a single-layer neural network?
Neuron
Node
Synapse
Perceptron
In deep learning, what does the term "backpropagation" refer to?
Forward movement of data
Learning from mistakes
Rewinding the network
Initialization of weights
What is the purpose of an activation function in a neural network?
Adjusting weights
Reducing bias
Introducing non-linearity
Controlling iterations
Which type of neural network is commonly used for image recognition tasks?
Feedforward Neural Network (FNN)
Recurrent Neural Network (RNN)
Convolutional Neural Network (CNN)
Artificial Neural Network (ANN)
What role does the "bias" play in a neural network?
Adjusting the overall influence of inputs
Reducing computation time
Controlling learning rate
Initializing weights
What is the primary purpose of the "loss function" in training a neural network?
Initializing weights
Evaluating model performance
Reducing bias
Controlling learning rate
Who is the god father of AI?
Alan Turing
Geoffrey Hinton
Elon Musk
John McCarthy
Which type of neural network is suitable for sequential data, such as time series or natural language processing?
Feedforward Neural Network (FNN)
Recurrent Neural Network (RNN)
Convolutional Neural Network (CNN)
Radial Basis Function Network (RBFN)
Which layer of a neural network is responsible for making the final predictions?
Input layer
Hidden layer
Output layer
Convolutional layer
In an ANN, what does the term "feedforward" refer to?
Forward propagation of data
Backward propagation of errors
Initializing weights
Adjusting the learning rate
Who Am I? I influence the importance of input features in training a neural network.
Weights
Bias
Activation Function
Loss Function
What is the output range of the sigmoid activation function?
[-1, 1]
[0, 1]
[-∞, ∞]
[0.5, 1]
1. What is the primary purpose of a Convolutional Neural Network (CNN)?
a) Object detection
b) Image classification
c) Text generation
d) Reinforcement learning
A
B
C
D
Which layer type is typically used to extract local features in a CNN?
a) Convolutional layer
b) Pooling layer
c) Fully connected layer
d) Activation layer
A
B
C
D
What is the advantage of using convolutional layers in a CNN?
a) They can capture local spatial patterns in the input data
b) They can handle sequential data
c) They can generate synthetic data
d) They can handle variable-length inputs
A
B
C
D
What is the purpose of the pooling layer in a CNN?
a) To reduce the spatial dimensions of the feature maps
b) To introduce non-linearity to the network
c) To adjust the weights and biases of the network
d) To compute the gradients for backpropagation
A
B
C
D
Which activation function is commonly used in the convolutional layers of a CNN?
a) ReLU (Rectified Linear Unit)
b) Sigmoid
c) Tanh (Hyperbolic Tangent)
d) Softmax
A
B
C
D
What is the purpose of the stride parameter in a convolutional layer?
a) To determine the size of the receptive field
b) To control the step size of the convolution operation
c) To adjust the learning rate during training
d) None of the above
A
B
C
D
Which layer type is used to reduce the spatial dimensions in a CNN?
a) Convolutional layer
b) Pooling layer
c) Fully connected layer
d) Activation layer
A
B
C
D
What is the purpose of data augmentation in CNN training?
a) To increase the number of layers in the network
b) To introduce noise and variations in the training data
c) To adjust the learning rate during training
d) None of the above
A
B
C
D
What is the purpose of the learning rate in CNN training?
a) To control the step size of the parameter updates during optimization
b) To adjust the size of the filters in the convolutional layers
c) To increase the number of layers in the network
d) None of the above
A
B
C
D
What is the purpose of the loss function in CNN training?
a) To measure the prediction error and guide the learning process
b) To initialize the weights and biases of the network
c) To adjust the learning rate during training
d) None of the above
A
B
C
D
Which layer type is commonly used in CNNs to normalize the input data?
a) Convolutional layer
b) Pooling layer
c) Batch normalization layer
d) Activation layer
A
B
C
D
Which layer type is responsible for parameter sharing in a CNN?
a) Convolutional layer
b) Pooling layer
c) Fully connected layer
d) Activation layer
A
B
C
D
What is the primary advantage of using a CNN over a fully connected neural network for image processing tasks?
a) CNNs have a higher training speed
b) CNNs can handle sequential data
c) CNNs have a higher number of neurons
d) CNNs can capture local spatial patterns in the input data
A
B
C
D
What is the purpose of dropout regularization in a CNN?
a) To increase the number of layers in the network
b) To adjust the learning rate during training
c) To randomly disable neurons during training to prevent overfitting
d) None of the above
A
B
C
D
What is the purpose of the fully connected layers in a CNN?
a) To capture global patterns and make predictions
b) To reduce the spatial dimensions of the input data
c) To apply non-linear transformations to the feature maps
d) To initialize the weights and biases of the network
A
B
C
D
Which of the following is NOT supervised learning?
Decision Tree
Linear Regression
Naive Bayes
Clustering
A Machine Learning method that is concerned with how software agents should take actions in an environment is
Reinforcement learning
semi- supervised learning
unsupervised learning
supervised learning
What is the objective of backpropagation algorithm?
to develop learning algorithm for multilayer feedforward neural network
to develop learning algorithm for single layer feedforward neural network
to propagate the computed loss to compute gradient
all the mentioned
What are general limitations of back propagation rule? Pick the right choice from the given options
i) local minima problem
ii) slow convergence
iii) scaling
only i
both ii and i
both ii and iii
i, ii and iii
Feedback networks are used for?
auto association
pattern storage
both auto association & pattern storage
pattern recognition
Number of output cases depends on what factor?
number of inputs
number of distinct classes
total number of classes
none of the mentioned
_________ is used to find local minima of the cost function
stochastic gradient descent
gradient descent
linear regression
logistic regression
Cost function(J) of Linear Regression is the _______ value between predicted y value (predicted) and true y value (y)
Mean
Root mean square
Median
Mean square
A = 1/(1 + e-x) is an equation representing which activation function?
ReLU
Sigmoid
Leaky ReLu
Tanh
The algorithm creates a line or a hyperplane which separates the data into classes and also suitable for classification and regression
K-means clustering
Support vector machine
Bayesian inference
perceptron
What steps can we take to prevent overfitting in a Neural Network?
Data Augmentation
Early Stopping
Dropout
Regularization
All the mentioned
Identify the activation function from the given diagram
Sigmoid, ReLU
ReLU, Leaky ReLU
ReLU, Tanh
TanH, ReLU
___________uses the processing of the brain as a basis to develop algorithms that can be used to model complex patterns and prediction problems.
ANN
CNN
RNN
KNN
How many possible layers can be there in deep neural network
1
≥ 50
10
no limit
In VC dimensions of neural networks what does VC stand for?
Vladimir Cherubim
Vapnik Chervonenkis
Victor Charlie
Vanessa Carlton
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
50
Less than 50
More than 50
It is an arbitrary value
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?
[1 X 5] , [5 X 8]
[8 X 5] , [ 1 X 5]
[8 X 5] , [5 X 1]
[5 x 1] , [8 X 5]
Which of the following neural network training challenge can be solved using batch normalization?
Overfitting
Restrict activations to become too high or low
Training is too slow
All the mentioned
For a binary classification problem, which of the following architecture would you choose?
1
2
Any one of these
None of these
The red curve above denotes training accuracy with respect to each epoch in a deep learning algorithm. Both the green and blue curves denote validation accuracy.
Green Curve
Blue Curve
Red Curve
None
