Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Video course · 10 chapters · 218 min · certificate

Machine Learning & Neural Networks without Libraries – No Black Box Course

Learn machine learning with no libraries by building a drawing classifier from scratch: code review, data cleaning, confusion matrices, distance-based features like elongation and roundness, vector vs raster data, and hand-built neural networks, optimisation and deep networks.

Become a memberAlready a member? Sign in

What you'll learn

  • Build ML without libraries
  • Clean and prepare data
  • Evaluate with a confusion matrix
  • Engineer features like elongation and roundness
  • Work with raster pixel data
  • Build and optimise neural networks from scratch

Chapters

10 chapters · 217:32
  1. 4:07 01Intro Members Introduction No black box.
  2. 19:04 02Review Members Phase 1 code review Drawing app.
  3. 18:19 03Cleaning Members Data cleaning Remove bad data.
  4. 34:30 04Evaluation Members Confusion matrix Where it errs.
  5. 23:23 05Features Members Distance and elongation Feature space.
  6. 19:57 06Roundness Members Measuring roundness Another feature.
  7. 23:20 07Pixels Members Vector vs raster Accessing pixels.
  8. 42:09 08Neural nets Members Neural networks From scratch.
  9. 20:26 09Optimisation Members Optimising neural networks Better values.
  10. 12:17 10Deep Members Deep neural networks More layers.