ML engineers, take note: structured ML reference guide

Link: https://ml-cheatsheet.readthedocs.io/en/latest/

There are no courses, no redundant theory, and no lengthy lectures here, but there are clear formulas, algorithms, the logic of ML pipelines, and a neatly structured knowledge base.

👉 @codeprogrammer

LandingAI released a free course on Document AI. It teaches how to build document processing pipelines that extract text, tables, charts, and forms without losing the context of the markup.

The problem with classic OCR is that it "extracts letters", but breaks the meaning:

- tables lose their structure (including merged cells)
- the connections "chart ⬅️➡️ signature" fall apart
- the reading order in multi-column becomes a mess

The course shows how to build an agent-workflow that reads documents closer to how a human does it, through Agentic Document Extraction (ADE).

What's inside:

- why regular OCR fails on complex documents
- how layout detection + correct reading order preserve the structure
- how to parse PDF into Markdown/JSON and not lose the layout
- how to collect RAG with ADE and vector databases
- how to deploy event-driven document pipelines on AWS

3 hours, 6 practical code examples. Completely free.

https://www.deeplearning.ai/short-courses/document-ai-from-ocr-to-agentic-doc-extraction/

👉 @DataScienceN