Let’s say, a “Linear regression†model perfectly fits the training data (train error is zero). Now, Which of the following statement is true?
1. You will always have test error zero
2.You can not have test error zero
3.both (a) and (b)
4.None of the above
scikit-learn also provides a class for per-sample normalization,_____
1.Normalizer
2.Imputer
3.Classifier
4.All of the above
A supervised scenario is characterized by the concept of a _____.
1.Programmer
2.Teacher
3.Author
4.Farmer
Function used for linear regression in R is __________
1.lm(formula, data)
2. lr(formula, data)
3. lrm(formula, data)
4.regression.linear(formula, data)
How do you handle missing or corrupted data in a dataset?
1.Drop missing rows or columns
2.Replace missing values with mean/median/mode
3.Assign a unique category to missing values
4.All of the above
If there is only a discrete number of possible outcomes called _____.
1.Modelfree
2.Categories
3.Prediction
4.None of the above
In order to assess how much information is brought by each component, and the correlation among them, a useful tool is the_____.
1. Concuttent matrix
2.Convergance matrix
3.Supportive matrix
4.Covariance matrix
In reinforcement learning, this feedback is usually called as___.
1.Overfitting
2.Overlearning
3.Reward
4.None of the above
Let’s say, you are working with categorical feature(s) and you have not looked at the distribution of the categorical variable in the test data. You want to apply one hot encoding (OHE) on the categorical feature(s). What challenges you may face if you have applied OHE on a categorical variable of train dataset?
1.All categories of categorical variable are not present in the test dataset.
2.Frequency distribution of categories is different in train as compared to the test dataset.
3. Train and Test always have same distribution.
4. Both A and B
scikit-learn offers the class______, which is responsible for filling the holes using a strategy based on the mean, median, or frequency
1.LabelEncoder
2.LabelBinarizer
3.DictVectorizer
4.Imputer
Suppose you are building a SVM model on data X. The data X can be error prone which means that you should not trust any specific data point too much. Now think that you want to build a SVM model which has quadratic kernel function of polynomial degree 2 that uses Slack variable C as one of it’s hyper parameter.What would happen when you use very large value of C(C->infinity)?
1.We can still classify data correctly for given setting of hyper parameter C
2.We can not classify data correctly for given setting of hyper parameter
3.Can’t Say
4.None of these
Suppose, you got a situation where you find that your linear regression model is under fitting the data. In such situation which of the following options would you consider?1. I will add more variables2. I will start introducing polynomial degree variables3. I will remove some variables
1.1 and 2
2. 2 and 3
3.1 and 3
4.1, 2 and 3
The SVM’s are less effective when:
1.The data is linearly separable
2.The data is clean and ready to use
3.The data is noisy and contains overlapping points
4.None of the above
We usually use feature normalization before using the Gaussian kernel in SVM. What is true about feature normalization? 1. We do feature normalization so that new feature will dominate other 2. Some times, feature normalization is not feasible in case of categorical variables3. Feature normalization always helps when we use Gaussian kernel in SVM
1.1
2.1 and 2
3. 1 and 3
4.2 and 3
Which of the following are several models for feature extraction
1.classification
2.regression
3.Both A and B
4.None of the above
Which of the following is true about “Ridge†or “Lasso†regression methods in case of feature selection?
1.Ridge regression uses subset selection of features
2.Lasso regression uses subset selection of features
3.Both use subset selection of features
4.None of these
Which of the following option is true regarding “Regression†and “Correlation†?Note: y is dependent variable and x is independent variable.
1.The relationship is symmetric between x and y in both.
2.The relationship is not symmetric between x and y in both.
3.The relationship is not symmetric between x and y in case of correlation but in case of regression it is symmetric.
4.The relationship is symmetric between x and y in case of correlation but in case of regression it is not symmetric.
Which of the following option is true regarding “Regression†and “Correlation†?Note: y is dependent variable and x is independent variable.
1. The relationship is symmetric between x and y in both.
2. The relationship is not symmetric between x and y in both.
3. The relationship is not symmetric between x and y in case of correlation but in case of regression it is symmetric.
4. The relationship is symmetric between x and y in case of correlation but in case of regression it is not symmetric.
Which of the following statement(s) can be true post adding a variable in a linear regression model?1. R-Squared and Adjusted R-squared both increase2. R-Squared increases and Adjusted R-squared decreases3. R-Squared decreases and Adjusted R-squared decreases4. R-Squared decreases and Adjusted R-squared increases
1.1 and 2
2.1 and 3
3.2 and 4
4.None of the above
Which of the following statements about Naive Bayes is incorrect?
1. Attributes are equally important.
2.Attributes are statistically dependent of one another given the class value. C. C.
3.Attributes are statistically independent of one another given the class value.
4.Attributes can be nominal or numeric
. If Linear regression model perfectly first i.e., train error is zero, then ____________
1. Test error is also always zero
2.Test error is non zero
3.Couldn’t comment on Test error
4.Test error is equal to Train error
. In many classification problems, the target dataset is made up of categorical labels which cannot immediately be processed by any algorithm. An encoding is needed and scikit-learn offers at least_____valid options
1.1
2.2
3.3
4.4
Common deep learning applications / problems can also be solved using____
1. Real-time visual object identification
2.Classic approaches
3.Automatic labeling
4.Bio-inspired adaptive systems
Hyperplanes are _____________boundaries that help classify the data points.
1.usual
2.decision
3.parallel
4.None of These
In a linear regression problem, we are using “R-squared†to measure goodness-of-fit. We add a feature in linear regression model and retrain the same model.Which of the following option is true?
1.If R Squared increases, this variable is significant.
2. If R Squared decreases, this variable is not significant.
3.Individually R squared cannot tell about variable importance. We can’t say anything about it right now.
4.None of the above
In a linear regression problem, we are using “R-squared†to measure goodness-of-fit. We add a feature in linear regression model and retrain the same model.Which of the following option is true?
1. If R Squared increases, this variable is significant.
2.If R Squared decreases, this variable is not significant.
3.Individually R squared cannot tell about variable importance. We can’t say anything about it right now.
4.None of These
In syntax of linear model lm(formula,data,..), data refers to ______
1.Matrix
2.Vector
3.Array
4.List
In the last decade, many researchers started training bigger and bigger models, built with several different layers that's why this approach is called_____.
1. Deep learning
2.Machine learning
3.Reinforcement learning
4.Unsupervised learning
overlearning causes due to an excessive ______.
1.Capacity
2.Regression
3.Reinforcement
4.Accuracy
Some people are using the term ___ instead of prediction only to avoid the weird idea that machine learning is a sort of modern magic.
1.Inference
2.Interference
3.Accuracy
4.None of the above
Suppose we fit “Lasso Regression†to a data set, which has 100 features (X1,X2…X100). Now, we rescale one of these feature by multiplying with 10 (say that feature is X1), and then refit Lasso regression with the same regularization parameter.Now, which of the following option will be correct?
1.It is more likely for X1 to be excluded from the model
2.It is more likely for X1 to be included in the model
3.Can’t say
4.None of These
Suppose we fit “Lasso Regression†to a data set, which has 100 features (X1,X2…X100). Now, we rescale one of these feature by multiplying with 10 (say that feature is X1), and then refit Lasso regression with the same regularization parameter.Now, which of the following option will be correct?
1.It is more likely for X1 to be excluded from the model
2.It is more likely for X1 to be included in the model
3.Can’t say
4.None of these
Suppose you are building a SVM model on data X. The data X can be error prone which means that you should not trust any specific data point too much. Now think that you want to build a SVM model which has quadratic kernel function of polynomial degree 2 that uses Slack variable C as one of it’s hyper parameter.What would happen when you use very small C (C~0)?
1.Misclassification would happen
2.Data will be correctly classified
3.Can’t say
4.None of these
Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes relationship of bias and variance with lambda.
1.In case of very large lambda; bias is low, variance is low
2. In case of very large lambda; bias is low, variance is high
3.In case of very large lambda; bias is high, variance is low
4. In case of very large lambda; bias is high, variance is high
The cost parameter in the SVM means:
1.The number of cross-validations to be made
2.The kernel to be used
3.The tradeoff between misclassification and simplicity of the model
4.None of the above
The term _____ can be freely used, but with the same meaning adopted in physics or system theory.
1.Accuracy
2.Cluster
3.Regression
4.Prediction
The _____of the hyperplane depends upon the number of features.
1. dimension
2.classification
3.reduction
4.None of these
The_____ parameter can assume different values which determine how the data matrix is initially processed.
1. run
2.start
3.init
4.stop
To test linear relationship of y(dependent) and x(independent) continuous variables, which of the following plot best suited?
1.Scatter plot B. C.
2.Barchart
3.Histograms
4.None of these
We can also compute the coefficient of linear regression with the help of an analytical method called “Normal Equationâ€. Which of the following is/are true about “Normal Equationâ€?1. We don’t have to choose the learning rate2. It becomes slow when number of features is very large3. No need to iterate
1.1 and 2
2. 1 and 3.
3. 2 and 3.
4.1,2 and 3.
what is the function of ‘Unsupervised Learning’?
1.Find clusters of the data and find low-dimensional representations of the data
2.Find interesting directions in data and find novel observations/ database cleaning
3.Interesting coordinates and correlations
4.All
What is the purpose of performing cross-validation?
1. To assess the predictive performance of the models
2.To judge how the trained model performs outside the sample on test data C. c.
3.Both A and B
4.None of These
What is/are true about kernel in SVM?1. Kernel function map low dimensional data to high dimensional space2. It’s a similarity function
1.1
2.2
3.1 and 2
4. None of these
Which of the following is not supervised learning?
1.PCA
2.Decision Tree
3.Naive Bayesian
4.Linerar regression
Which of the following is true about “Ridge†or “Lasso†regression methods in case of feature selection?
1.Ridge regression uses subset selection of features B.
2.Lasso regression uses subset selection of features
3. Both use subset selection of features
4.None of above
Which of the following is true about Naive Bayes ?
1.Assumes that all the features in a dataset are equally important
2.Assumes that all the features in a dataset are independent
3.both (a) and (b)
4.None of the above option
Which of the following statement is true about outliers in Linear regression?
1.Linear regression is sensitive to outliers
2. Linear regression is not sensitive to outliers
3.Can’t say
4.None of these
which of the following step / assumption in regression modeling impacts the trade-off between under-fitting and over-fitting the most.
1. The polynomial degree
2. Whether we learn the weights by matrix inversion or gradient descent
3.The use of a constant-term
4.None of these
While using _____ all labels areturned into sequential numbers.
1.LabelEncoder class
2.LabelBinarizer class
3.DictVectorizer
4.FeatureHasher
_ provides some built-in datasets that can be used for testing purposes.
1.scikit-learn
2.classification
3.regression
4.None of the above
_is the most drastic one and should be considered only when the dataset is quite large, the number of missing features is high, and any prediction could be risky.
1.Removing the whole line
2.Creating sub-model to predict those features
3.Using an automatic strategy to input them according to the other known values
4.All above
__which can accept a NumPy RandomState generator or an integer seed.
1.make_blobs
2.random_state
3. test_size
4.None of these
___can be adopted when it's necessary to categorize a large amount of data with a few complete examples or when there's the need to impose some constraints to a clustering algorithm.
1.Supervised
2.Semi-supervised
3.Reinforcement
4.Clusters
___produce sparse matrices of real numbers that can be fed into any machine learning model.
1.DictVectorizer
2.FeatureHasher
3.Both A & B
4.None of the Mentioned
_____dataset with many features contains information proportional to the independence of all features and their variance.
1.normalized
2.unnormalized
3.Both A and B
4.None of the Mentioned