|
2 | 2 | "cells": [ |
3 | 3 | { |
4 | 4 | "cell_type":"markdown", |
5 | | -"id":"bef2427e-273d-4515-a608-42732f01fc3e", |
| 5 | +"id":"e805c2fa-5123-40e9-8044-24d4feb1b09f", |
6 | 6 | "metadata": {}, |
7 | 7 | "source": [ |
8 | | -"# Gradient Descent\n", |
9 | | -"\n", |
10 | | -"[Gradient descent](https://en.wikipedia.org/wiki/Gradient_descent) is a simple algorithm for finding the minimum of a function of multiple variables. It works on the principle of looking at the local gradient of a function then then moving in the direction where it decreases the fastest.\n", |
11 | | -"\n", |
12 | | -"Note: there is no guarantee that you arrive at the global minimum instead of a local minimum." |
| 8 | +"# Gradient Descent" |
| 9 | + ] |
| 10 | + }, |
| 11 | + { |
| 12 | +"cell_type":"markdown", |
| 13 | +"id":"e6a5307c-2881-4d78-9bda-cad6552da6cf", |
| 14 | +"metadata": {}, |
| 15 | +"source": [ |
| 16 | +"[Gradient descent](https://en.wikipedia.org/wiki/Gradient_descent) is a simple algorithm for finding the minimum of a function of multiple variables. It works on the principle of looking at the local gradient of a function then then moving in the direction where it decreases the fastest." |
| 17 | + ] |
| 18 | + }, |
| 19 | + { |
| 20 | +"cell_type":"markdown", |
| 21 | +"id":"6baa1ac3-05d2-44fc-8089-6b6260370a0e", |
| 22 | +"metadata": {}, |
| 23 | +"source": [ |
| 24 | +"```{important}\n", |
| 25 | +"There is no guarantee that you arrive at the global minimum instead of a local minimum.\n", |
| 26 | +"```" |
13 | 27 | ] |
14 | 28 | }, |
15 | 29 | { |
|
329 | 343 | "name":"python", |
330 | 344 | "nbconvert_exporter":"python", |
331 | 345 | "pygments_lexer":"ipython3", |
332 | | -"version":"3.12.2" |
| 346 | +"version":"3.13.2" |
333 | 347 | } |
334 | 348 | }, |
335 | 349 | "nbformat":4, |
|