// ⬡ Deep Learning Foundations

Perceptron

The first artificial neuron: weighted sum followed by a threshold.

感知机 1958 Beginner core

IN PLAIN WORDS

Multiply inputs by weights, sum, and fire if above threshold; nudge weights when wrong. Alone it draws only linear boundaries — stacking layers gives modern networks.

Used in: Historical starting point of neural networks

TIMELINE · prerequisites → this → what builds on it

1958 Perceptron1986 Backpropagati…2016 GELU

01Original paper

The perceptron: A probabilistic model for information storage and organization in the brain.

Rosenblatt et al. · Psychological Review · 1958

DOI ↗ ✓ Verified · Crossref API doi:10.1037/h0042519

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

No prerequisites — a good starting point

Perceptron

Then you can learn

Related:Logistic Regression

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Video

3Blue1Brown ↗EN

Books

Deep Learning ↗EN

04Where the course teaches it

U22 Linear Models, SVM & Nearest Neighbors From the perceptron to maximum margin and the kernel trick, plus k-nearest neighbours. 6 h5 algorithms2 papers U30 Neural Networks & Backpropagation From neurons and multilayer perceptrons to backpropagation and activation functions. 10 h4 algorithms2 paperslesson ready

On learning paths:Zero to Deep Learning

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: perceptron)