Domain Neighborhood
Calculus
Rates of change and accumulation. Calculus is the language behind gradients, optimization, continuous-time dynamics, and why backprop works as efficiently as it does.
Recommended Route
Start here, then follow the prerequisites forward.
This sequence is ordered for learning rather than inventory: lower difficulty, fewer prerequisites, and more central concepts come first.
- 01Computation Graphs
A computation graph breaks a calculation into nodes so values flow forward and sensitivities flow backward.
13 mincodedemoafter Chain RuleCheck Chain Rule first if the symbols feel slippery.
- 02Derivatives
The derivative is an instantaneous rate of change: the slope you get when a secant line becomes a tangent line.
14 mincodedemoafter FunctionsWhy this follows: both pages keep the calculus thread active.
- 03Backpropagation
Backpropagation applies reverse-mode autodiff to neural networks so one scalar loss can train many parameters.
15 mincodedemoafter Reverse-Mode Automatic DifferentiationWhy this follows: both pages keep the calculus thread active.
- 04Reverse-Mode Automatic Differentiation
Reverse-mode autodiff computes gradients by sending cotangents backward through a computation graph.
14 mincodedemoafter Computation GraphsWhy this follows: both pages keep the calculus thread active.
All Published Notebooks
Browse the territory.
Computation Graphs
A computation graph breaks a calculation into nodes so values flow forward and sensitivities flow backward.
Derivatives
The derivative is an instantaneous rate of change: the slope you get when a secant line becomes a tangent line.
Backpropagation
Backpropagation applies reverse-mode autodiff to neural networks so one scalar loss can train many parameters.
Reverse-Mode Automatic Differentiation
Reverse-mode autodiff computes gradients by sending cotangents backward through a computation graph.
In Progress