Search Your Question...!

Deep Learning basic MCQ's

 1)What is the difference between the actual output and generated output known as? 

Output Modulus 

Accuracy 

Cost 

Output Difference 

Answer:-Cost 


(2)Recurrent Neural Networks are best suited for Text Processing. 

True 

False 

Answer:-True 


(3)Prediction Accuracy of a Neural Network depends on _______________ and ______________. 

Input and Output 

Weight and Bias 

Linear and Logistic Function 

Activation and Threshold 

Answer:-Weight and Bias 


(4)Recurrent Networks work best for Speech Recognition. 

True 

False 

Answer:-True 


(5)GPU stands for __________. 

Graphics Processing Unit 

Gradient Processing Unit 

General Processing Unit 

Good Processing Unit. 

Answer:- Graphics Processing Unit 


(6)Gradient at a given layer is the product of all gradients at the previous layers. 

False 

True 

Answer:- True 


(7)_____________________ is a Neural Nets way of classifying inputs. 

Learning 

Forward Propagation 

Activation 

Classification 

Answer:- Forward Propagation 


(8)Name the component of a Neural Network where the true value of the input is not observed. 

Hidden Layer 

Gradient Descent 

Activation Function 

Output Layer 

Answer:- Hidden Layer 


(9)________________ works best for Image Data. 

AutoEncoders 

Single Layer Perceptrons 

Convolution Networks 

Random Forest 

Answer:- Convolution Networks 


(10)Neural Networks Algorithms are inspired from the structure and functioning of the Human Biological Neuron. 

False 

True 

Answer:- True 


(11)In a Neural Network, all the edges and nodes have the same Weight and Bias values. 

True 

False 

Answer:- False 


(12)_______________ is a recommended Model for Pattern Recognition in Unlabeled Data. 

CNN 

Shallow Neural Networks 

Autoencoders 

RNN 

Answer:- Autoencoders 


(13)Process of improving the accuracy of a Neural Network is called _______________. 

Forward Propagation 

Cross Validation 

Random Walk 

Training 

Answer:- Training 


(14)Data Collected from Survey results is an example of ___________________. 

Data 

Information 

Structured Data 

Unstructured Data 

Answer:- Structured Data 


(15)A Shallow Neural Network has only one hidden layer between Input and Output layers. 

False 

True 

Answer:- True 


(16)Support Vector Machines, Naive Bayes and Logistic Regression are used for solving ___________________ problems. 

Clustering 

Classification 

Regression 

Time Series 

Answer:- Classification 


(17)The rate at which cost changes with respect to weight or bias is called __________________. 

Derivative 

Gradient 

Rate of Change 

Loss 


(18)What does LSTM stand for? 

Long Short Term Memory 

Least Squares Term Memory 

Least Square Time Mean 

Long Short Threshold Memory 

Answer:-Long Short Term Memory 


(19)All the Visible Layers in a Restricted Boltzmannn Machine are connected to each other. 

True 

False 

Answer:- False 


(20)All the neurons in a convolution layer have different Weights and Biases. 

True 

False 

Answer:- False 


(21)What is the method to overcome the Decay of Information through time in RNN known as? 

Back Propagation 

Gradient Descent 

Activation 

Gating 

Answer:- Gating 


(22)Recurrent Network can input Sequence of Data Points and Produce a Sequence of Output. 

False 

True 

Answer:- True 


(23)A Deep Belief Network is a stack of Restricted Boltzmann Machines. 

False 

True 

Answer:-True 


(24)Restricted Boltzmann Machine expects the data to be labeled for Training. 

False 

True 

Answer:- False 


(25)What is the best Neural Network Model for Temporal Data? 

Recurrent Neural Network 

Convolution Neural Networks 

Temporal Neural Networks 

Multi Layer Perceptrons 

Answer:- Recurrent Neural Network 


(26)RELU stands for ______________________________. 

Rectified Linear Unit 

Rectified Lagrangian Unit 

Regressive Linear Unit 

Regressive Lagrangian Unit 

Answer:- Rectified Linear Unit 


(27)Why is the Pooling Layer used in a Convolution Neural Network? 

They are of no use in CNN. 

Dimension Reduction 

Object Recognition 

Image Sensing 

Answer:- Dimension Reduction 


(28)What are the two layers of a Restricted Boltzmann Machine called? 

Input and Output Layers 

Recurrent and Convolution Layers 

Activation and Threshold Layers 

Hidden and Visible Layers 

Answer:- Hidden and Visible Layers 


(29)The measure of Difference between two probability distributions is know as ________________________. 

Probability Difference 

Cost 

KL Divergence 

Error 

Answer:- KL Divergence 


(30)A _________________ matches or surpasses the output of an individual neuron to a visual stimuli. 

Max Pooling 

Gradient 

Cost 

Convolution 

Answer:- Convolution 


(31)The rate at which cost changes with respect to weight or bias is called __________________. 

Derivative 

Gradient 

Rate of Change 

Loss 

Answer:- Gradient 


(32)Autoencoders are trained using _____________________. 

Feed Forward 

Reconstruction 

Back Propagation 

They do not require Training 

Answer:- Back Propagation 


(33)How do RNTS interpret words? 

One Hot Encoding 

Lower Case Versions 

Word Frequencies 

Vector Representations 

Answer:-Vector Representations 


(34)De-noising and Contractive are examples of __________________. 

Shallow Neural Networks 

Autoencoders 

Convolution Neural Networks 

Recurrent Neural Networks 

Answer:-Autoencoders 


(35)Autoencoders cannot be used for Dimensionality Reduction. 

False 

True 

Answer:-False


(36)Recursive Neural Tensor Nets  models are best suited for Recursive Data.

No comments:

Post a Comment