---
title: "ML fundamentals | Grigory Gulyuk"
description: "Loss, training, approximation and generalisation. Everything on this site about ML fundamentals."
canonical_url: "https://gulyuk.com/topics/ml-fundamentals"
meta:
  "og:description": "Loss, training, approximation and generalisation. Everything on this site about ML fundamentals."
  "og:image": "https://gulyuk.com/og-image.png"
  "og:image:alt": "Grigory Gulyuk, gulyuk.com"
  "og:image:height": "630"
  "og:image:width": "1200"
  "og:title": "ML fundamentals | Grigory Gulyuk"
  "twitter:image": "https://gulyuk.com/og-image.png"
  "twitter:image:alt": "Grigory Gulyuk, gulyuk.com"
---

> Index of every page on this site: [llms.txt](https://gulyuk.com/llms.txt)

[← AI & ML](https://gulyuk.com/topics/ai)

# ML fundamentals

Loss, training, approximation and generalisation.

1 idea

- 16 Oct 2026 · research · [AI & ML](https://gulyuk.com/topics/ai) ·  budding ## [Machine learning is function approximation](https://gulyuk.com/ideas/function-approximation)

  A model is a function you cannot write down, so you build one out of simple parts and tune it until it fits. An interactive walk through the standard parts, and what each is good and bad at.
  - [ML fundamentals](https://gulyuk.com/topics/ml-fundamentals)
  - [Maths](https://gulyuk.com/topics/math)
  - [Interactive explainers](https://gulyuk.com/topics/explainers)

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://gulyuk.com/#website","@type":"WebSite","description":"Notes, experiments and a CV by Grigory Gulyuk, a software engineer working on AI tooling and full-stack products.","name":"Grigory Gulyuk","url":"https://gulyuk.com/","publisher":{"@id":"https://gulyuk.com/#identity"}},{"@id":"https://gulyuk.com/topics/ml-fundamentals#webpage","@type":"WebPage","description":"Loss, training, approximation and generalisation. Everything on this site about ML fundamentals.","name":"ML fundamentals","url":"https://gulyuk.com/topics/ml-fundamentals","breadcrumb":{"@id":"https://gulyuk.com/topics/ml-fundamentals#breadcrumb"},"isPartOf":{"@id":"https://gulyuk.com/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://gulyuk.com/topics/ml-fundamentals"]}]},{"@id":"https://gulyuk.com/#identity","@type":"Person","name":"Grigory Gulyuk","url":"https://gulyuk.com","sameAs":["https://www.linkedin.com/in/gulyuk","https://github.com/BraindeadDogge"]},{"@id":"https://gulyuk.com/topics/ml-fundamentals#breadcrumb","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","name":"Home","item":"https://gulyuk.com","position":1},{"@type":"ListItem","name":"Ideas","item":"https://gulyuk.com/ideas","position":2},{"@type":"ListItem","name":"AI & ML","item":"https://gulyuk.com/topics/ai","position":3},{"@type":"ListItem","name":"ML fundamentals","position":4}]}]}
```

## Sitemap

See the full [sitemap](https://gulyuk.com/sitemap.md) for all pages.