0
Top 90 Deep Learning Questions Answers

Open 1 Answers 117 Views Technology
Top 90 Deep Learning Questions Answers

1 Answer

0
Deep learning is a part of machine learning with an algorithm inspired by the structure and function of the brain, which is called an artificial neural network. In the mid-1960s, Alexey Grigorevich Ivakhnenko published the first general, while working on deep learning network. Deep learning is suited over a range of fields such as computer vision, speech recognition, natural language processing, etc.

There are various applications of deep learning:

Computer vision

Natural language processing and pattern recognition

Image recognition and processing

Machine translation

Sentiment analysis

Question Answering system

Object Classification and Detection

Automatic Handwriting Generation

Automatic Text Generation.

Deep learning has brought significant changes or revolution in the field of machine learning and data science. The concept of a complex neural network (CNN) is the main center of attention for data scientists. It is widely taken because of its advantages in performing next-level machine learning operations. The advantages of deep learning also include the process of clarifying and simplifying issues based on an algorithm due to its utmost flexible and adaptable nature. It is one of the rare procedures which allow the movement of data in independent pathways. Most of the data scientists are viewing this particular medium as an advanced additive and extended way to the existing process of machine learning and utilizing the same for solving complex day to day issues.

Below are the different Deep Leaning Questions and answer are followed by the questions

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

(a) Output Modulus

(b) Accuracy

(c) Cost

(d) Output Difference

Correct Answer of the above questions is :Cost

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

(a) True

(b) False

Correct Answer of the above questions is :True

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

(a) Input and Output

(b) Weight and Bias

(c) Linear and Logistic Function

(d) Activation and Threshold

Correct Answer of the above questions is :Weight and Bias

(4)Recurrent Networks work best for Speech Recognition.

(a) True

(b) False

Correct Answer of the above questions is :True

(5)GPU stands for __________.

(a) Graphics Processing Unit

(b) Gradient Processing Unit

(c) General Processing Unit

(d) Good Processing Unit.

Correct Answer of the above questions is : Graphics Processing Unit

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

(a) False

(b) True

Correct Answer of the above questions is : True

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

(a) Learning

(b) Forward Propagation

(c) Activation

(d) Classification

Correct Answer of the above questions is : Forward Propagation

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

(a) Hidden Layer

(b) Gradient Descent

(c) Activation Function

(d) Output Layer

Correct Answer of the above questions is : Hidden Layer

(9)________________ works best for Image Data.

(a) AutoEncoders

(b) Single Layer Perceptrons

(c) Convolution Networks

(d) Random Forest

Correct Answer of the above questions is : Convolution Networks

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

(a) False

(b) True

Correct Answer of the above questions is : True

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

(a) True

(b) False

Correct Answer of the above questions is : False

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

(a) CNN

(b) Shallow Neural Networks

(c) Autoencoders

(d) RNN

Correct Answer of the above questions is : Autoencoders

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

(a) Forward Propagation

(b) Cross Validation

(c) Random Walk

(d) Training

Correct Answer of the above questions is : Training

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

(a) Data

(b) Information

(c) Structured Data

(d) Unstructured Data

Correct Answer of the above questions is : Structured Data

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

(a) False

(b) True

Correct Answer of the above questions is : True

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

(a) Clustering

(b) Classification

(c) Regression

(d) Time Series

Correct Answer of the above questions is : Classification

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

(a) Derivative

(b) Gradient

(c) Rate of Change

(d) Loss

(18)What does LSTM stand for?

(a) Long Short Term Memory

(b) Least Squares Term Memory

(c) Least Square Time Mean

(d) Long Short Threshold Memory

Correct Answer of the above questions is :Long Short Term Memory

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

(a) True

(b) False

Correct Answer of the above questions is : False

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

(a) True

(b) False

Correct Answer of the above questions is : False

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

(a) Back Propagation

(b) Gradient Descent

(c) Activation

(d) Gating

Correct Answer of the above questions is : Gating

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

(a) False

(b) True

Correct Answer of the above questions is : True

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

(a) False

(b) True

Correct Answer of the above questions is :True

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

(a) False

(b) True

Correct Answer of the above questions is : False

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

(a) Recurrent Neural Network

(b) Convolution Neural Networks

(c) Temporal Neural Networks

(d) Multi Layer Perceptrons

Correct Answer of the above questions is : Recurrent Neural Network

(26)RELU stands for ______________________________.

(a) Rectified Linear Unit

(b) Rectified Lagrangian Unit

(c) Regressive Linear Unit

(d) Regressive Lagrangian Unit

Correct Answer of the above questions is : Rectified Linear Unit

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

(a) They are of no use in CNN.

(b) Dimension Reduction

(c) Object Recognition

(d) Image Sensing

Correct Answer of the above questions is : Dimension Reduction

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

(a) Input and Output Layers

(b) Recurrent and Convolution Layers

(c) Activation and Threshold Layers

(d) Hidden and Visible Layers

Correct Answer of the above questions is : Hidden and Visible Layers

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

(a) Probability Difference

(b) Cost

(c) KL Divergence

Error

Correct Answer of the above questions is : KL Divergence

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

(a) Max Pooling

(b) Gradient

Cost

Convolution

Correct Answer of the above questions is : Convolution

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

(a) Derivative

(b) Gradient

(c) Rate of Change

(d) Loss

Correct Answer of the above questions is : Gradient

(32)Autoencoders are trained using _____________________.

(a) Feed Forward

(b) Reconstruction

(c) Back Propagation

(d) They do not require Training

Correct Answer of the above questions is : Back Propagation

(33)How do RNTS interpret words?

(a) One Hot Encoding

(b) Lower Case Versions

(c) Word Frequencies

(d) Vector Representations

Correct Answer of the above questions is :Vector Representations

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

(a) Shallow Neural Networks

(b) Autoencoders

(c) Convolution Neural Networks

(d) Recurrent Neural Networks

Correct Answer of the above questions is :Autoencoders

(35)Autoencoders cannot be used for Dimensionality Reduction.

(a) False

(b) True

Correct Answer of the above questions is :False
by (54.6k points)
...