Categories

If I want to apply regression analysis to the deaths caused by bike accidents, what would be the dependent variable in this case? Number of Deaths Number of people sitting on bike Place of accident Insufficient Information

Which of the following cannot be solved with Linear Regression? Predicting stock prices Predicting wastage of food(in kgs) in each city. Predicting if a person would get married at age of 25. Predicting the weather forecast.

Which of the following is not a factor for the types of regression algorithms? Number of independent variables Number of rows or Number of data points Type of target column Shape of regression line

Outliers do not affect linear regression algorithm as anyway it fits a straight line? True False

Regression cannot be used for discrete values. True False

Choose the category of machine learning you will use to train a model to play pac-man? Supervised Learning Unsupervised Learning Reinforcement Learning Any of the above will work fine

Which of the following is NOT true pertaining to Data Preparation? Data preparation involves crawling data from different sources and coming up with a dataset which resembles real-world data. There is no need of data preparation in case of supervised learning Unsupervised learning removes the dependency on data preparation as no labels are required Data preparation can be outsourced to companies providing data preparation services.

Choose the category of machine learning you will use to train a model to reduce the number of features of a dataset (or reduce dimensions)? Supervised Learning Unsupervised Learning Reinforcement Learning Any of the above will work fine

Choose the ONLY correct statement? Supervised Learning algorithms can get more complex than Unsupervised Learning if data volume increases. Unsupervised Learning algorithms are usually more complex than Unsupervised Learning Reinforcement Learning algorithms are always simple, no matter the use case. All of the Above

Choose the category of machine learning you will use to train a model to predict whether a user would buy a product or not? Supervised Learning Unsupervised Learning Reinforcement Learning Any of the above will work fine

On applying dimensional reduction, how much variance should be retained in the data ideally? 10% - 15% 50% - 60% 90% - 100% Doesn't matter

Which of the following is not a type of unsupervised learning? Clustering Dimensionality Reduction Regression Association Learning

Which of the following is a "Clustering" Problem? Predicting Stock Prices Predicting power consumption in a factory Grouping news articles as per their categories. Predicting salary of a new employee

A Dataset for a unsupervised learning problem should contain? Only Features (Input Data) Features and Labels for corresponding features. Only Labels (Output Data) None of the above

Which among the following is NOT an advantage of unsupervised learning? Independent of the labeling of the data Gives high accuracy models. Finds out hidden patterns in the data. Works with varying number of classes.

A Dataset for a supervised learning problem should contain? Only Features (Input Data) Features and Labels for corresponding features. Only Labels (Output Data) None of the above

In which year did Bruno, Goodnow and Austin define Concept Learning? 1964 1965 1966 1967

Select the correct flow a supervised machine learning pipeline. Data Ingestion -> Data Cleaning -> EDA -> Model Training and Evaluation -> Prediction Data Cleaning -> Data Ingestion -> EDA -> Model Training and Evaluation Data Ingestion -> Model Training and Evaluation -> Data Cleaning -> EDA -> Prediction Data Ingestion -> Data Cleaning -> Model Training and Evaluation -> EDA ->Prediction

Which of the following is a "Classification" Problem? Predicting Stock Prices Predicting the type of cancer from images Predicting salary of a new employee Predicting power consumption in a factory

Which among the following is NOT a disadvantage of supervised learning? Highly dependent on the labeling of the data Doesn't infer any hidden patterns in the data. Doesn't work with varying number of output labels. Data understanding is better as classes are predefined.

Introduction to Regression

Supervised vs Unsupervised Learning

Unsupervised Machine Learning

Machine Learning - Basic

Supervised Machine Learning

Join the Club!

Get all the latest blog updates directly in your mailbox and stay ahead of the curve.

Yes, I'm IN!

Join and Stay ahead of the curve.