ML Concepts Quiz

What are the three main cloud service models?

• FaaS

• IaaS, PaaS, SaaS

• MaaS

• DaaS

Explain the difference between IaaS, PaaS, and SaaS.

• SaaS offers computing resources

• PaaS provides software applications

• IaaS stands for Internet as a Service

• IaaS provides computing resources, PaaS offers a platform for application development, and SaaS delivers software applications.

What is Azure ML Workbench used for?

• Designing websites

• Creating music playlists

• Cooking recipes

• Building, training, and deploying machine learning models

How can data preprocessing techniques help in machine learning?

• Data preprocessing techniques help in cleaning and transforming raw data into a suitable format for training machine learning models, improving model performance and accuracy.

• Data preprocessing techniques help in generating random data for machine learning models.

• Data preprocessing techniques are only useful for visualizing data in machine learning.

• Data preprocessing techniques hinder the performance of machine learning models.

List some common data preprocessing techniques.

• Data normalization

• Data aggregation

• Data cleaning, Data transformation, Data encoding, Data scaling, Feature engineering

• Data validation

What is feature engineering in machine learning?

• Feature engineering is the process of training a model without any data preprocessing.

• Feature engineering is the process of removing variables from the dataset.

• Feature engineering is the process of selecting and transforming variables or features to improve model performance.

• Feature engineering involves only selecting features without any transformation.

Why is feature engineering important in ML?

• Feature engineering is not important in ML

• Feature engineering only adds complexity to models

• Feature engineering does not impact model performance

• Feature engineering helps in creating new input features from existing data that can improve the performance of machine learning models.

Give examples of feature engineering methods.

• Label encoding

• Regularization

• One-hot encoding, feature scaling, polynomial features, feature selection

• Dimensionality reduction

How does feature selection differ from feature engineering?

• Feature selection focuses on selecting the most relevant features, while feature engineering involves creating new features or transforming existing ones.

• Feature selection is only applicable to numerical features, while feature engineering is only applicable to categorical features.

• Feature selection and feature engineering are the same concepts.

• Feature selection involves creating new features, while feature engineering focuses on selecting the most relevant features.

Discuss the impact of feature engineering on model performance.

• Feature engineering always leads to overfitting

• Feature engineering has no impact on model performance

• Feature engineering only works for specific types of models

• Feature engineering can significantly impact model performance by providing more relevant information to the model, capturing complex patterns and relationships in the data, and ultimately leading to better predictions.