Machine learning

What is Machine Learning (ML)?

Branch of AI where machines learn from data to make decisions or predictions without being explicitly programmed.

What is the difference between AI and ML?

• AI is the broader field of creating intelligent machines.

• ML is a subset of AI that focuses on machines learning from data.

What is supervised learning?

• Learning using labeled data where the machine is trained with input-output pairs to make predictions.

• Predicting house prices

What is unsupervised learning?

• Learning using unlabeled data where the machine groups or finds patterns without predefined categories.

• Customer segmentation

What is reinforcement learning?

• Learning through trial and error where the machine learns by receiving rewards or penalties for actions.

• RWhat is training data?obot learning to walk by trying movements

What is training data?

The dataset used to teach a machine learning model.

What is testing data?

Data used to evaluate how well a trained model performs on new, unseen inputs.

What is a model in ML?

A mathematical representation of a real-world process learned from training data.

What is clustering?

Grouping unlabeled data points by similarity.

What is K-means?

A centroid-based clustering algorithm that assigns points to nearest cluster center and updates centers iteratively.

What is hierarchical clustering?

Builds nested clusters by merging or splitting

What is DBSCAN?

• Density-based clustering that finds clusters of high point density and marks noise.

What is classification?

• Assigning discrete labels to inputs using labeled training data.

• Decision trees and logistic regression.

What is KNN?

• K-Nearest Neighbors; an instance-based classifier that labels a point by majority vote of its K nearest training samples.

• The number of neighbors used to decide the label.

• Euclidean distance (for numeric features).

How does increasing K affect KNN?

Smooths the decision boundary and reduces variance; may increase bias.

What is regression?

Predicting continuous numerical outputs from input features.