Learning Outcome1: Differentiate Various Types of Learning in ML
Q1. How many types of machine learning?
a) 5 b)4 c)6 d)3
(b) 4
Q2.Identify the one which is not a type of learning.
a) Reinforcement Learning b)Unsupervised Learning
c)Semi-supervised Learning d)Semi unsupervised Learning
(d)Semi unsupervised Learning
Q3. Who is the father of Machine Learning?
a)Geoffrey Everest Hinton b)Geoffrey Hill
c)Geoffrey Chaucer d)Geoffrey Bawa
a)Geoffrey Everest Hinton
Q4.SML stands for_____________.
a) Super vised Machine Learning b)Super view Machine Learning
c) Special Machine Learning d)Special vised Machine Learning.
(a) Super vised Machine Learning
Q5.ANN also known as___________.
a)Atomic Neural Network b)Artificial Network Network
c)Artificial Neural Network d)Atmosphere Neural Network
c)Artificial Neural Network
Q6 . Which one is a subset of Machine Learning.
a)Artificial Intelligence b)Deep Learning
c) Data Mining d)Cloud Computing
b)Deep Learning
Q 7.ANN can perform task......
a)prediction b)decision making c)visualization d) all of these
d) all of these
Q8.Recognition patterns is used for.
a)facial expression b)Facial Identification
c)only A d)Both A and B
d)Both A and B
Q9. Markov decision process is used in
a)Supervised learning b)Unsupervised learning
c)Semi-supervised Learning d)Reinforcement Learning
d)Reinforcement Learning
Q 10.Unsupervised learning_________?
a) Deals with the unlabeled data b) Creating data
c) is a source d)none of these
a) deals with the unlabeled data
Q11 . Text document classifier is an example of
a)Supervised learning b)Unsupervised learning
c)Semi-supervised Learning d)Reinforcement Learning
c)Semi-supervised Learning
Q12.ML is a field of AI consisting of learning algorithms that?
a) At executing some task b)improve their performance
c)Over time with experience d)All of the above
d)All of the above
Q13.What is the successful application of ML.
a) Learning to drive an autonomous vehicle. b)Learning to recognize spoken words
c)Learning to classify new astronomical structures d)All of the above
d) All of the above
Q14.Which of the following does not include different learning methods?
a)Analog b) Memorization c)Deduction d)Introduction
d) Introduction
Q15.Which one of the not a supervised learning ?
a)PCA b)Linear Regression c)Decision Tree Answer d)Naive Bayesian
a)PCA
Learning Outcome 2: Explain Regression ,Type and Metrics.
Q1. Generally, which of the method(s) is used for predicting continuous dependent variable?
a) linear regression b) logistic regression c) none of these d) both a) and b)
b) logistic regression
Q2. Regression is a part of
a) supervised learning algorithm b)unsupervised Learning algorithm
c)semi supervised learning algorithm d)reinforcement learning algorithm
a) supervised learning algorithm
Q3. how many types of Regression equation .
a)2 b)3 c)4 d)5
a)2
Q4. Which of the following options is true regarding regression.
a) It is used for prediction and interpretation. b)It relates input and output
c) Only a) is true d)Both a) and b) are true
d)Both a) and b) are true
Q5. Linear regression is_______.
a) a machine learning algorithm b) an Input
c) an output d) none of the above
a) a machine learning algorithm
Q6. Linear regression is used for.......
a) image recognition b) value store
c) predictive analysis d) for radiation
c) predictive analysis
Q7. Identify the one is used to create the most common graph type?
a) quickeplot b) plot c) aplot d) none of the above
a)quickplot
Q8. MES stand for...........?
a)Minimum squared Error b)Maximum squared Error
c)Mean squared Error d)Main squared Error
c)Mean squared Error
Q9. how to work MSE?
a)Measure the amount of error b)Increase the error
c)Decrease the error d)None of these
a)Measure the amount of error
Q10.Full form of MAE
a) Mean Absolute Error b)Message Absolute Error
c)Message Address Error d)Mean Address Error
a) Mean Absolute Error
Q11. The deviation of the measured value from the true value is called error. It is also known as a ______?
a)Value b)Data c)Static Error d)none of the following
c)Static Error
Q12. FIND-S Algorithm ignores are
a)Positive b)Negative c)Both a) and b) d) None of the above
b)Negative
Q.13. What kind of learning algorithm for "Future stock prices or currency exchange rates"? a)Prediction b) Recognition pattern c)Generating pattern d)None of these
a)Prediction
Q.14. What is the relationship between model and algorithm?
a)Data = Algorithm (model) b)Algorithm=Model +data
c)Algorithm +Model =data d)Model = Algorithm(data)
d) Model = Algorithm(data)
Q.15. Logistic regression is used to?
a)describe data and to explain the relationship b)store the data
c)multiply the data d) none of these
a)describe data and to explain the relationship
Learning Outcome 4: Differentiate Tree and Random Forest Classifier.
Q1. What do you mean by classifier?
a) It is an input
b) An algorithm that automatically orders or categorizes data into one or more of a set of classes.
c)Is the end result of your machine learning.
d)All of these
b) An algorithm that automatically orders or categorizes data into one or more of a set of classes.
Q2. In which category, we define the classifiers-
a) supervised b)unsupervised c)only a) d)both
d) both
Q3. What is the use of decision tree?
a)for decision making b)explicitly represent decision c)for visually d) all of above
Q4. Decision tree can be used in
a. Classifier b. Regression
a) only a b) only b c) Both (a) & (b) d) Neither (a) nor (b)
c) Both (a) & (b)
Q.5. Which one is a decision tree nodes?
a)Decision Nodes b)End Nodes c)Chance Nodes d)All of these
d)all of these
Q6. Decision Nodes are represented by_____?
a) Squares b)Triangles c)Circles d)Disks
a) Squares
Q7. Chance Nodes are represented by_____?
a) Squares b)Triangles c)Circles d)Disks
c)Circles
Q8.End Nodes are represented by_____?
a) Squares b)Triangles c)Circles d)Disks
b)Triangles
Q9. What is a decision support tool that uses a tree -like graph or model of decision?
a)Tree b)Graph c)Neural Network d)Decision tree
d)Decision tree
Q3.With the help of a confusion matrix, we can compute.
Q10.Which of the following nodes are Decision Tree Nodes?
a)End Nodes b)Decision Nodes c)Chance Nodes d) All of these
d) All of these
Q11.__________is a display of algorithm.
a)End Nodes b)Decision Nodes c)Chance Nodes d)Simple Nodes
b)Decision Nodes
Q12.
Learning Outcome 5: Define various performance measure matrix in ML.
Q1. Classification accuracy is_____
a)a subdivision of a set of examples into a number of classes
b)the task of assigning a classification to a set of examples
c)measure of the accuracy, of the classification of a concept that is given by a certain theory.
d)none of these
c)measure of the accuracy, of the classification of a concept that is given by a certain theory.
Q2.What is the full form of TN?
a)True Negative b)True Narration c)Tunneling network d)text next
a)True Negative
a)error rate b)accuracy c)precision d) all of above
d) all of above
Q4. In the confusion matrix columns represented are____
a)Actual Values b)Predicted Values c)both d)none of these
a)Actual Values
Q5. In the confusion matrix rows represented are____
a)Actual Values b)Predicted Values c)both d)none of these
b)Predicted Values
Q6. What is the full form of ROC curve
a)receiver operating characteristic curve b)receiver opening characteristic curve
c)recall operating characteristic curve d)resell operating characteristic curve
a)receiver operating characteristic curve
Q7.What is the use of ROC?
a)for data managing b) for Graphing c) both d)none of these
b) for Graphing
Q8.How many parameters in ROC model.
a)4 b)6 c)8 d)2
d)2
Q9. What is the full form of TPR?
a) total peripheral resistance b) True Positive Rate
c)temperature pulse respiration d)none of these
b) True Positive Rate
Q10. What is the full form of FPR?
a)Forward pricing Rate b)Final Positive Rate
c)False Positive Rate d)None of these
c)False Positive Rate
Q11.AUC stands for?
a) Area under the roc curve b)Authenticated user community
c) Average unit cell d)Area under communication
a) Area under the roc curve
Q12.
Learning Outcome:6 Illustrate ANN , Perceptron and Concept of Backpropagation.
Q1. What is the full form of ANN?
a)Artificial Neural Network b) Amine news network
c)Active Node network d)Announcer Netreview net
a)Artificial Neural Network
Q2. How many types of Artificial Neural Network?
a)5 b)6 c)2 d)7
c)2
Q3.In which ANN ,loops are allowed?
a) FeedBack ANN b)Forward ANN c)both d)none of these
c)both
Q4)What is the full form of BN?
a)Belief Networks b)Bayes Net c)Bayesian Networks d) All of these
d) All of these
Q5. Which year first ANN are invented?
a)1958 b)1957 c)1985 d)1858
a)1958
Q6. What is the need of biological neural network?
a) Make smart human interactive and user friendly system
b) Make Humans lazy
c)both A and B
d)None of these
a) Make smart human interactive and user friendly system
Q7. What is the fundamental unit of network ?
a)Brain b)Neuron c)Systems d)nucleus
d)nucleus
Q8.What is perceptron ?
a)a single layer feed-forward neural network with pre- processing
b) an auto- associative neural network
c) a double layer auto- associative neural network
d) a neural network that contains feedback
a)a single layer feed-forward neural network with pre- processing
Q9. What is the full form of MLP?
a)Multi layer Perceptron b)message link protocol
c)multi level parallelism d)multi layer protocol
a)Multi layer Perceptron
Q10.A Multilayer perceptron is a ______?
a)feed forward artificial neural network
b)feed Backward artificial neural network
c) both
d) none of the above
a)feed forward artificial neural network
Q11. MLP generates a set of______?
a )output b)input c) solutions d)data
a )output
Q12. MLP uses backpropagation for_____?
a) training the network b) store the data
c) cover the network d) none of these
a) training the network
Q13.How many layer consist an MLP?
a)2 b)3 c)4 d)5
a)2
Q14.Backpropogation law is also known as
a)learning rule b)solving rule c)record rule d)Delta rule
d)Delta rule
Q15. Backpropagation network is
a)A neural network that makes use of a hidden layer
b)it is a form of automatic learning
c)both
d)none of the above
a)A neural network that makes use of a hidden layer
Learning Output: 7 Explain convolutional neural Network
Q1. What is the full form of CNN?
a)Cable News Network b)
c) Convolutional Neural Network d)
c) Convolutional Neural Network
Q2. CNN are used for_______?
a) image recognition b)image processing
c)object detection d)all of these
d)all of these
Q3.What is a role of input layer in CNN?
a)It contain image data b)create several smaller picture
c)identify and classify the objects in the image d)It resides at the end of the FC layer
a)It contain image data
Q4.Pooling layer is also known as?
a)spatial pooling layer b)subsampling
c)down sampling d) All of above
d) All of above
Q5.CNN is mostly used when?
a)structured data b) unstructured data
c) both d) none of the above
Learning Outcome 8: Differentiate CNN and RNN.
Q1. What is the full form of RNN?
a)Removable Neural Network b)Recurring Neural Network
c)Recurrent Neural Network d)Recursive Neural Network
c)Recurrent Neural Network
Q2. One of the most important features of RNN is_______?
a)Hidden State b)Visible State c)Present State d)None of these
a)Hidden State
Q3.Which direction move the information in feed forward neural network?
a) Only one direction b)Back direction
c) Both direction d) No direction
a) Only one direction
Q4.What are the main uses of RNN?
a)sequence classification b)sequence Labelling
c)sequence generation d)All of the above
d)All of the above
Q5. LSTM stands for ?
a) Left-short term memory b)Long-short terminology memory
c) Long-short term memory d)Long-short technology memory
c) Long-short term memory
Q6. What is "gradient" in RNN?
a)A parameter that can help you improve the algorithm's accuracy
b)the art algorithm for sequential data
c)Part of speech tagging and named entity recognition
d)ability to develop an internal representation of a two-dimensional image.
a)A parameter that can help you improve the algorithm's accuracy
Q7. What are the advantage of RNN architecture?
a)Computation being slow
b)Difficulty of accessing information from a long time ago
c)Cannot consider an future input for the current state
d)Model size not increasing with size of input
d)Model size not increasing with size of input
Q8.What is the full form of GRU?
a)General Resources Unit b)Grid Reference Unit
c)Gated Recurrent Unit d)Grid Resources Unit
c)Gated Recurrent Unit
Q9.Sequence prediction problems include-
a)one-to-many b) Many- to - One
c)Many-to-Many d) All of these
d) All of these
Learning Outcome 9:Discuss Deep Learning concepts and It's application
Q1.What is right about correlation in Machine Learning?
a)cannot accurately describe curvilinear relationships.
b)Explain how variables related to each other
c)Explain linear variables
d)Explain non-linear variables
b)Explain how variables related to each other
Q2.How many possible results of a correlational study?
a) 3 b)4 c)5 d)6
a) 3
Q4.In which correlation the value of one variable increase then value of the other variable (s) also increases.
a)positive correlation b)negative correlation
c) no correlation d) none of the above
a)positive correlation
Q5.In negative correlation ?
a)when the value of one variable increase or decrease then the value of the other variable(s) doesn't increase or decreases.
b)the value of one variable increase then value of the other variable (s) also increases.
c)the value of one variable increase then value of the other variable(s) decreases.
d) none of the above
c)the value of one variable increase then value of the other variable(s) decreases.
Q6.In negative correlation variables are __________?
a)positively correlated with each other
b)negatively correlated with each other
c)not correlated with each other
d)none of the above
b)negatively correlated with each other
Q7.No correlation means:
a)when the value of one variable increase or decrease then the value of the other variable(s) doesn't increase or decreases.
b)the value of one variable increase then value of the other variable (s) also increases.
c)the value of one variable increase then value of the other variable(s) decreases.
d) none of the above
a)when the value of one variable increase or decrease then the value of the other variable(s) doesn't increase or decreases.
Q8Which neural network has only one hidden layer between the input and output ?
a)Recurrent neural networks
b)Deep neural networks
c)Shallow neural networks
d)Feed-forward neural networks
c)Shallow neural networks
Learning Outcome 10:Discuss the importance of Activation function in ANN
Q1.What is binary step function?
a) a linear function b)non-linear function
c) linear activated function d)a threshold-based activation function
d)a threshold-based activation function
Q2.The sigmoid transforms the values between the _______?
a)0 and 1 b)1 and 2 c) 2 and 1 d)2 and 3
a)0 and 1
Q3. Which type of function is sigmoid?
a)Linear function b) non-linear function
c)linear activation function d)non-linear activation function
b) non-linear function
Q4.Which type of function is ReLU?
a)non-linear activation function b)linear activation function
c)both a)and b) d) None of these
a)non-linear activation function
Q5.ReLU stands for?
a)Recorded Linear Unit b)Removable Linear Unit
c)Rectified Linear Unit d)Regression Linear Unit
c)Rectified Linear Unit
Q6.What is the main advantage of ReLU function?
a)It activate all the neurons at the same time
b)It does not activate all the neurons at the same time
c)It activate some neurons at the same time
d)It does not activate the neurons
b)It does not activate all the neurons at the same time
Q7.What is Leaky ReLU?
a)It activate all the neurons at the same time
b)It does not activate all the neurons at the same time
c)It activate some neurons at the same time
d)just advance version of ReLU function
d)just advance version of ReLU function
Q8.ELU stands for?
a)Enduring landscape Units
b)Environmental load Units
c)Exponential Linear Unit
d)Environmental Linear Unit
c)Exponential Linear Unit
Q9.What does ELU?
a)modifies the slope of the negative part or the function
b)modifies the slope of the positive part or the function
c)Both a) and b)
d)None of the above
a)modifies the slope of the negative part or the function
Q10.Which layer is used in the ReLU function?
a)Hidden layer b)input layer c)output layer d)all layers are used
a)Hidden layer
Q11.What is the use of Softmax function?
a)for single classification problems
b)for double classification problems
c)for multiclass classification problems
d)None of the above
c)for multiclass classification problems
Learning Outcome 11:Impleament Support vector Machine Classifier
Q1.What is the full form of SVM?
a)Supplier vector Machine b)Support Vector Machine
c)Support Vector Mechanism d) Supplier Vector Mechanism
b)Support Vector Machine
Q2.What problem can be solved in SVM?
a)Image classification b)Recognizing handwriting
c)Caner detection d) All of these
d) All of these
Q3.Support Vector Machine is____________?
a)classification learning b)Unsupervised Machine Learning
c)Supervised Machine Learning d)reinforcement learning
c)Supervised Machine Learning
Q4.__________ can't learn directly learned?
a)System vector machine b)Support vector networks
c)System vector navigation d)hyperparameters
d)hyperparameters
Q5. What is a full form of NLP?
a)Natural Language Processing b)Non-linear programming
c)Neural Linguistic Programming d)Nero Linguistic Programming
a)Natural Language Processing
Q6.What are the applications of Deep Learning?
a)Self Driving Car b)Deep Dreaming
c)Pixel restoration d)All of these
d)All of these
Q7.SVR stands for?
a)Standard variable Rate b)Smart Video recorder
c)Standard Vector Rate d)Support Vector regression
d)Support Vector regression
Q8. Which parameters are used in SVM
a)Kernel b)Hyperplane
c)Decision Boundary d)All of the above
d)All of the above
Well-set-questions..!! :)
ReplyDelete