Super Accessible No Math Intro to Neural Networks For Beginners
summary
Claims that neural networks are simple math processes using only addition/subtraction; they learn by warping input data toward a fixed guess via iterative feedback rather than mimicking brains. Concrete demo: missing GPA emerges as a hidden factor when multiple predictors are combined and a dataset shift of 21 years aligns ages to the legal‑drinking threshold. Pitfalls cited: opaque latent features, the wolf/dog model that keys on snowy backgrounds, and a mugshot model that detects smiles not criminality.
AI-written summary · about
chapters (14)
- 0:00Neural networks for beginners
- 1:05Neural networks vs human brains
- 2:30Quantifying relationships
- 4:42Finding best factors
- 7:12What is a neural network
- 10:21Learning by warping data
- 13:54Neural network process
- 16:00Recap of mechanics
- 16:42Drawbacks of networks
- 18:48Ethical pitfalls
- 20:10Language models vs basic networks
- 21:12Challenges in new types
- 22:40What to learn first
- 24:10Q&A
related talks
40mNeural Networks: Where do I start?!?
01h 51mUnderstanding Neural Networks (Somewhat)
43mA Gentle Introduction to Neural Networks
41mUnveiling the simple math that powers AI
52mNeural Networks Walkthrough
44mMachine Learning Exposed
06mLearn Neural Networks With Go—Not Math! (Interview)
33mLearn Neural Networks With Go - Not Math!