Watch a single artificial neuron compute: weights, bias, and one activation function
TinfoilTricorn · x · 2026-11-20
A visual explainer of how little a single artificial neuron actually does: three inputs are scaled by weights, summed with a bias, and passed through one squashing function. The live demo lets you watch activations switch between sigmoid, tanh, and ReLU — with ReLU, anything below zero simply doesn't fire — while every number updates in real time as the weights drift.
More from Research
- Team claims Codex cracked 35 open Erdős problems in 2 months, some Lean-verified — IgorCarron · 2026-11-20
- ForgeSystem paper proposes AI agents forging demand-specific software — Div_pradeep · 2026-11-20
- Accord: open-source dense metric mapping from a single camera and IMU — BE2R · 2026-11-20
- AltRA-Test: ~100 samples suffice to decide if LLM judges can replace humans — Technion · 2026-11-20
- TwinD hits 95.6% AUROC on face synthesis deepfakes, beating prior detectors — Andrii Yermakov · 2026-11-20
- Frostbite: A new CPU architecture discovered, designed and verified by AI — shioyama · 2026-11-20