Multi-Layer Perceptron
Physics-Informed Neural Networks (PINNs)
DeepONet: Operator Learning with Neural Networks
Differentiable Simulation
Graph Neural Network
Lab Setup

Computing gradients with Automatic Differentiation

The Core Insight:

Functions Are Computational Graphs.

Every computer program that evaluates a mathematical function can be viewed as a computational graph. Consider this simple function:

This creates a computational graph where each operation is a node. This decomposition is the key insight that makes automatic differentiation possible.

Back
 
Next
©  |   Cornell University    |   Center for Advanced Computing    |   Copyright Statement    |   Access Statement
CVW material development is supported by NSF OAC awards 1854828, 2321040, 2323116 (UT Austin) and 2005506 (Indiana University)