Podcast
Using Visualizations to Explain Machine Learning: Build Intuition with kDimensions, Figma & Templates
Open original DataTalks.Club episode
Using Visualizations to Explain Machine Learning: Build Intuition with kDimensions, Figma & Templates
Original Episode
Use these links for the canonical episode and media sources.
- Open the original DataTalks.Club podcast page
- Watch on YouTube
- Listen on Spotify
- Listen on Apple Podcasts
Episode Overview
How do you teach machine learning so people build intuition before diving into math? In this episode, Meor Amer—educator, author, and Developer Relations at Cohere—walks through a visual-first approach to machine learning that makes concepts accessible and actionable. Drawing on his journey from bioengineering and telecom analytics to founding kDimensions and writing A Visual Introduction to Deep Learning, Meor explains why visual machine learning and dimensionality reduction matter and how templates can scale.
People
Use these links to connect the episode to guest notes.
Chapter Summary
Use these checkpoints to decide whether to open the source transcript.
- 0:00 - Episode Introduction & Visual ML Overview
- 1:56 - Posting Cadence & Visuals on LinkedIn
- 2:57 - Career Journey: Bioengineering → Telecom Analytics → Self-employment
- 6:15 - kDimensions: Name & Visual Dimensionality Reduction
- 8:52 - Jack Butcher Influence & Visual Engineering Principles
- 11:40 - Purpose of Visuals: Build Intuition Before Math
- 14:12 - Design Constraints: Creativity Through Color & Shape Limits
- 17:33 - Idea Generation: Visualize the Verb & Use Metaphors
- 21:26 - Drift Visualized (Catapult Metaphor) & Data-centric AI Airplane Analogy
- 24:07 - Creative Process: Longlist → Shortlist → Brainstorming
- 30:26 - Capturing Ideas: Sketchbook, Notes & Quick Logging
- 31:14 - Tools: Figma for Engineers & Geometric Shape Workflow
- 33:31 - From Sketch to Figma: Drafting, Asset Reuse & Iteration
- 35:32 - Design Advice: Prioritize Message Over Aesthetics; Start Posting
- 40:50 - Learning Technique: Consume with Intent to Teach — “What If?” Questions
- 43:37 - Hands-on Learning: Break and Modify Code to Understand ML
- 44:47 - Monetization: Visual Design Services for Startups & Content Creators
- 49:00 - Content Design: Turn Articles into Key Visuals (Extract 4–5 Keywords)
- 50:56 - Visualization Techniques: Contrast, Balance & Slider Metaphors
- 54:06 - Mapping ML Problems to Visual Templates: Classification, Regression, Anomaly,
- 56:01 - Book Overview: Visual Introduction to Deep Learning (Neuron-by-Neuron)
- 58:56 - Book Workflow: Visual-first Layout with Concise Text