Font size
WorksheetsLesson 2 : Introduction to Machine Learning
Total questions: 20
Worksheet time: 10mins
What are the common approaches for encoding categorical data
One hot encoding
Standardization
Ordinal encoding
The scaling technique where we rescale the data to have mean = 0 and standard deviation = 1
Standardization
Normalization
What is the typical pipeline for a classification model using text data?
vectorize text > normalize text > train model > deploy model
train model > normalize text > vectorize text > deploy model
normalize text > vectorize text > deploy model > train model
normalize text > vectorize text > train model > deploy model
Channels present in RGB color coding
Red
Grey
Blue
Green
Open-source tool that can combine code, markdown, and visualizations together in a single document.
Visual Studio
Visual Studio Code
Jupyter Notebook
Categorical datatype is otherwise called as
Discrete
Continuous
Mark all the following fields in which Machine Learning is used
extract patterns from data
allowing computers to identify related data
forecast future outcomes
make predictions or identify important relationships
A broad term that refers to computers thinking more like humans.
Artificial Intelligence
Machine Learning
Deep Learning
Common types of data in Machine Learning
Time Series
Categorical
Object
Image
Numerical
At what stage of the data science lifecycle do you optimize the parameters?
Data collection
Train the model
Prepare Data
Evaluate Model
In which technique you can depict a relation between two variable using a straight line
Linear regression
Logistic regression
Gradient Descent
Greedy algorithms
_____ algorithms do not make assumptions regarding the form of the mapping between input data and output, so they are free to learn any functional form from the training data.
Parametric
Non Parametric
Which one of them finds hidden structures in data
linear regression
Supervised learning
UnSupervised learning
Error that results from inaccurate assumptions in model training (that are made to simplify the training process)
Variance
Overfitting
Underfitting
Bias
In the regression equation Y = a+bX, the Y is called:
Independent variable
Continuous variable
Dependent variable
None of the above
In simple linear regression model Y = α + βX + ε where α and β are called:
Estimators
Parameters
Random errors
Variables
The purpose of simple linear regression analysis is to:
Replace points on a scatter diagram by a straight-line
Obtain the expected value of the independent random variable for a given value of the dependent variable
Predict one variable from another variable
True- False: Overfitting is more likely when you have huge amount of data to train?
TRUE
FALSE
The most commonly used cost function for linear regression is
Bias
RMSE
Variance
Which of these comes in data preparation?
Removing collinearity
Rescale data
Remove noise
Evaluation metrics
