Q.1 __________ is a Neural Nets way of classifying inputs.
A. Classification
B. Learning
C. Forward Propagation
D. Activation
Ans : Learning
Q.2 Recurrent Neural Networks are best suited for Text Processing.
A. True
B. False
Ans : True
Q.3 Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron.
A. True
B. False
Ans : True
Q.4 The rate at which cost changes with respect to weight or bias is called _________.
A. Loss
B. Gradient
C. Rate of Change
D. Derivative
Ans : Gradient
Q.5 __________ is a recommended Model for Pattern Recognition in Unlabeled Data.
A. Autoencoders
B. CNN
C. RNN
D. Shallow Neural Networks
Ans : Autoencoders
Q.6 What does LSTM stand for?
A. Least Square Time Mean
B. Least Squares Term Memory
C. Long Short Term Memory
D. Long Short Threshold Memory
Ans : Long Short Term Memory
Q.7 RELU stands for __________.
A. Rectified Lagrangian Unit
B. Rectified Linear Unit
C. Regressive Lagrangian Unit
D. Regressive Linear Unit
Ans : Rectified Linear Unit
Q.8 All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other.
A. True
B. False
Ans : False
Q.9 A Deep Belief Network is a stack of Restricted Boltzmann Machines.
A. True
B. False
Ans : True
Q.10 All the neurons in a convolution layer have different Weights and Biases.
A. True
B. False
Ans : False
Q.11 A Shallow Neural Network has only one hidden layer between Input and Output layers.
A. True
B. False
Ans : True
Q.12 GPU stands for __________.
A. General Processing Unit
B. Graphics Processing Unit
C. Gradient Processing Unit
D. Good Processing Unit
Ans : Graphics Processing Unit
Q.13 Autoencoders cannot be used for Dimensionality Reduction.
A. True
B. False
Ans : True
Q.14 A _______________ matches or surpasses the output of an individual neuron to a visual stimuli.
A. Convolution
B. Max Pooling
C. Cost
D. Gradient
Ans : Convolution
Q.15 Name the component of a Neural Network where the true value of the input is not observed.
A. Hidden Layer
B. Output Layer
C. Gradient Descent
D. Activation Function
Ans : Activation Function
Q.16 What is the best Neural Network Model for Temporal Data?
A. Temporal Neural Networks
B. Multi Layer Perceptrons
C. Convolution Neural Networks
D. Recurrent Neural Network
Ans : Recurrent Neural Network
Q.17 The measure of Difference between two probability distributions is know as ___________.
A. KL Divergence
B. Probability Difference
C. Cost
D. Error
Ans : KL Divergence
Q.18 All the Visible Layers in a Restricted Boltzmann Machine are connected to each other.
A. True
B. False
Ans : True
Q.19 In a Neural Network, all the edges and nodes have the same Weight and Bias values.
A. True
B. False
Ans : True
Q.20 What is the difference between the actual output and generated output known as?
A. Output Difference
B. Output Modulus
C. Accuracy
D. Cost
Ans : Output Difference
Q.21 Process of improving the accuracy of a Neural Network is called __________.
A. Cross Validation
B. Random Walk
C. Forward Propagation
D. Training
Ans : Training
Q.22 Autoencoders are trained using _________.
A. They do not require Training
B. Back Propagation
C. Feed Forward
D. Reconstruction
Ans : Back Propagation
Q.23 Data Collected from Survey results is an example of __________.
A. Structured Data
B. Unstructured Data
C. Information
D. Data
Ans : Structured Data
Q.24 Support Vector Machines, Naive Bayes and Logistic Regression are used for solving ___________ problems.
A. Classification
B. Clustering
C. Time Series
D. Regression
Ans : Clustering
Q.25 Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output.
A. True
B. False
Ans : True
Q.26 Gradient at a given layer is the product of all gradients at the previous layers.
A. True
B. False
Ans : True
Q.27 What is the method to overcome the Decay of Information through time in RNN known as?
A. Gradient Descent
B. Back Propagation
C. Activation
D. Gating
Ans : Back Propagation
Q.28 Why is the Pooling Layer used in a Convolution Neural Network?
A. Image Sensing
B. Object Recognition
C. Dimension Reduction
D. They are of no use in CNN
Ans : Dimension Reduction
Q.29 Prediction Accuracy of a Neural Network depends on _______________ and ______________.
A. Activation and Threshold
B. Linear and Logistic Function
C. Weight and Bias
D. Input and Output
Ans : Input and Output
Q.30 ____________ works best for Image Data.
A. Convolution Networks
B. Single Layer Perceptrons
C. Random Forest
D. AutoEncoders
Ans : AutoEncoders
Q.31 ____________ models are best suited for Recursive Data.
A. Multi Layer Perceptrons
B. Convolutional Neural Networks
C. Recursive Neural Networks
D. Recursive Neural Tensor Nets
Ans : Recursive Neural Networks
