Calculus for Machine Learning

Name: Calculus for Machine Learning
Availability: InStock
Author: FreeAcademy

Intermediate

Assumes foundational knowledge. Builds on basics.

Master the calculus that powers machine learning. Learn derivatives, partial derivatives, the chain rule, gradients, gradient descent, loss functions, and backpropagation — the essential math behind how models learn.

Course Content

6 modules • 18 lessons

Derivatives: The Language of Change

3 lessons

1.1

Why Calculus Matters for Machine Learning

1.2

What Is a Derivative?

1.3

Derivative Rules You Actually Need

Partial Derivatives: Functions with Multiple Inputs

3 lessons

2.1

Functions of Several Variables

2.2

Partial Derivatives Explained

2.3

The Gradient Vector

The Chain Rule: Backbone of Backpropagation

3 lessons

3.1

The Chain Rule for Single Variables

3.2

The Chain Rule for Multiple Variables

3.3

Computational Graphs and the Chain Rule

Gradient Descent: How Models Learn

3 lessons

4.1

Introduction to Gradient Descent

4.2

Learning Rate and Convergence

4.3

Variants of Gradient Descent

Loss Functions and Optimization

3 lessons

5.1

Common Loss Functions in Machine Learning

5.2

The Optimization Landscape

5.3

Regularization and Overfitting

Backpropagation: Putting It All Together

3 lessons

6.1

How Neural Networks Learn

6.2

Backpropagation Step by Step

6.3

Backpropagation in Practice

Reviews

Calculus for Machine Learning

Intermediate

Assumes foundational knowledge. Builds on basics.

Course Content

6 modules • 18 lessons

Derivatives: The Language of Change

3 lessons

1.1

Why Calculus Matters for Machine Learning

1.2

What Is a Derivative?

1.3

Derivative Rules You Actually Need

Partial Derivatives: Functions with Multiple Inputs

3 lessons

2.1

Functions of Several Variables

2.2

Partial Derivatives Explained

2.3

The Gradient Vector

The Chain Rule: Backbone of Backpropagation

3 lessons

3.1

The Chain Rule for Single Variables

3.2

The Chain Rule for Multiple Variables

3.3

Computational Graphs and the Chain Rule

Gradient Descent: How Models Learn

3 lessons

4.1

Introduction to Gradient Descent

4.2

Learning Rate and Convergence

4.3

Variants of Gradient Descent

Loss Functions and Optimization

3 lessons

5.1

Common Loss Functions in Machine Learning

5.2

The Optimization Landscape

5.3

Regularization and Overfitting

Backpropagation: Putting It All Together

3 lessons

6.1

How Neural Networks Learn

6.2

Backpropagation Step by Step

6.3