Lior Sinai • 8/17/2024

MicroGrad.jl: Part 4 Extensions

Read Original

This technical article, part 4 of a series on automatic differentiation in Julia, details extending the MicroGrad.jl library. It explains how to implement pullbacks for core functions like `map`, `getproperty`, and anonymous functions—which lack formal mathematical derivatives—to create a generic gradient descent optimizer. The tutorial demonstrates this by fitting a polynomial model, addressing challenges not covered by standard ChainRules.jl.

0 comments
#julia #Gradient Descent #Automatic Differentiation
MicroGrad.jl: Part 4 Extensions

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
React, useEffect, and Stale Closures: How to Avoid Them with Dependencies and useRef
Jivbcoop • 4 votes
2
Better react-hook-form Smart Form Components
Maarten Hus • 2 votes
3
AGI, ASI, A*I – Do we have all we need to get there?
John D. Cook • 1 votes
4
Quoting Thariq Shihipar
Simon Willison • 1 votes
5
Dew Drop – January 15, 2026 (#4583)
Alvin Ashcraft • 1 votes
6
Using Browser Apis In React Practical Guide
Jivbcoop • 1 votes