SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-neuron-weighted-sum

What calculation does a basic artificial neuron perform before activation?

It forms a weighted sum plus a bias.

Start playing free

  1. Weighted sum plus bias ✔
  2. Median of its inputs
  3. Largest input only

Why: Each input is multiplied by its own weight. The products are added, then a bias is added before the activation function acts.

Huh, didn't know that: Changing one weight changes how strongly its matching input influences the neuron.

The dad joke
Why did the neuron carry a calculator? It had too many weighted decisions.
Like this card?
Play the game

References

Answer: Weighted sum plus bias. Each input is multiplied by its own weight. The products are added, then a bias is added before the activation function acts.

  1. Google Machine Learning Crash Course: Nodes and hidden layers developers.google.com/machine-learning/crash-course/neural-networks/nodes-hidden-layers
    take the sum of the product of each of its inputs (the neurons in the previous network layer) and a unique weight parameter, plus the bias
    Checked 2026-10-11.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceWhat can a neuron's bias change even when its inputs stay fixed?Artificial IntelligenceAfter query-key scores become weights, what does attention combine?Artificial IntelligenceHow do AI, machine learning and deep learning fit together?

That's stuff everyone should know.