Quiz 1: Basics of Machine Learning and Supervised Learning

What is Machine Learning primarily used for?

• Writing code

• Automating repetitive tasks

• Generating random numbers

• Compressing files

Answer explanation

Machine learning automates tasks by learning from data and making predictions or decisions without explicit programming.

What is the output of a regression model?

• Categorical labels

• Clusters of data

• Continuous values

• Binary classifications

Answer explanation

Regression models predict continuous values like prices, temperatures, or distances.

How does reinforcement learning work?

• It learns from labeled data

• It creates clusters of similar data

• It uses a decision tree to predict outcomes

• It uses rewards and punishments

Answer explanation

Reinforcement learning trains agents by maximizing rewards based on actions taken in an environment.

What does supervised learning require?

• Labeled data

• Data clusters

• A reward function

• A neural network

Answer explanation

Supervised learning relies on labeled datasets, where input-output pairs guide the learning process.

What type of learning does a spam filter use?

• Supervised learning

• Reinforcement learning

• Unsupervised learning

• Clustering

Answer explanation

Spam filters are trained on labeled datasets to classify emails as spam or not.

Which algorithm is best suited for predicting a salary based on years of experience?

• K-Means

• Neural Networks

• Decision Trees

• Linear Regression

Answer explanation

Linear regression models the relationship between years of experience (input) and salary (output)

What is the purpose of a loss function in supervised learning?

• To measure model error

• To split data into training and testing

• To choose the best model architecture

• To maximize accuracy

Answer explanation

The loss function calculates the difference between the predicted output and the actual label.

• What is the primary goal of unsupervised learning?

• Logistic RegressionPredicting labeled data

• Logistic Regression

• K-Means Clustering

• Support Vector Machine

Answer explanation

Unsupervised learning groups data based on patterns or similarities without needing labeled outcomes.

What does overfitting mean in machine learning?

• A model performs well on training data but poorly on new data

• A model is too simple

• A model has a high bias

• A model uses too many features

Answer explanation

Overfitting occurs when a model learns patterns specific to training data, failing to generalize to unseen data.

Which metric is commonly used to evaluate classification models?

• Mean Squared Error

• Accuracy

• R-squared

• Logarithmic Loss

Answer explanation

Accuracy measures the proportion of correctly classified instances out of the total instances.