Learning Machine Learning
summary
Practical entry path: start with data science basics, then use small experiments in TensorFlowJS or Python to verify claims — a linearly separable toy gets ~100% accuracy, a two‑moons set hits ~86% with a linear model but rises with a hidden layer, and an “amoeba” shape needs ~15 hidden nodes; generative models produce faces on thispersondoesnotexist. Operational work matters: ML ops, Kubernetes, edge inference (Fastly/Cloudflare) and deployment to phones often decide whether a project succeeds. Trained ~3,000 people and ran a viral video with ~100,000 views.
AI-written summary · about
chapters (7)
- 0:00Introduction to ML career
- 7:57Why machine learning matters
- 17:48Data-driven ML fundamentals
- 24:32ML specializations overview
- 31:12Data science workflow explained
- 37:56ML ops for developers
- 42:06Next steps and resources
related talks
42mLearning Machine Learning
37mMachine Learning Principles, with JavaScript?
51mHow to get started in Machine Learning
37mMachine Learning Principles, with JavaScript?
40mWhat is Machine Learning, and How Do I Get Started?
51mMachine Learning Exposed Introduction to Machine Learning
48mLearning Machine Learning
41mBeyond the Algorithm: What Makes Machine Learning Work?