Back to Numerical Computation
Session 8
Numerical Computation

Automatic Differentiation and Algorithmic Differentiation

4 hours
Duration
8
Materials
6
Objectives
Session Overview

Comprehensive treatment of automatic differentiation including forward and reverse modes, computational graphs, and applications in optimization and machine learning.

Learning Objectives
By the end of this session, you should be able to:
  • Understand forward mode automatic differentiation with dual numbers
  • Master reverse mode automatic differentiation and backpropagation
  • Implement computational graph construction and evaluation
  • Apply automatic differentiation to optimization problems
  • Use AD for gradient computation in machine learning applications
  • Compare automatic differentiation with numerical and symbolic differentiation
Course Materials
Download materials for offline study and reference
Automatic Differentiation Theory and Methods (50 pages)
Available material
Forward and Reverse Mode Implementations
Available material
Computational Graph Algorithms
Available material
Optimization Applications with Gradient Computation
Available material
Machine Learning Integration Examples
Available material
Performance Comparison Studies
Available material
Advanced AD Techniques and Tools
Available material
Complete AD Software Development Project
Available material