Math required for ML

Deals with vectors, matrices, and linear transformations.
Enables efficient representation and computation of data and models.
Core to understanding neural networks and optimization. 

Studies change through derivatives and integrals.
Used to optimize models by minimizing loss functions.
Essential for training algorithms via gradient-based methods. 

Models uncertainty and randomness in data.
Helps quantify likelihoods and make predictions.
Fundamental to Bayesian methods and probabilistic models. 

Provides tools to collect, summarize, and interpret data.

Helps identify patterns, trends, and uncertainty in datasets.

Forms the backbone of data-driven decision making in ML. 

Focuses on predicting continuous numerical values.
Learns relationships between input features and outputs.
Widely used for forecasting and trend analysis. 

Assigns data points to discrete categories or labels.
Learns decision boundaries from labeled examples.
Commonly used in tasks like spam detection and image recognition.