Knowledge Maxxing← Back to topic library
ML MaxxingAdvanced75 sec
Artificial neuron
An artificial neuron computes a weighted sum of its inputs, adds a bias term, and passes the result through an activation function to produce one output value.
Prerequisite: Linear regression
What matters
This simple computation, repeated across many neurons arranged in layers, is the basic building block that all neural networks are constructed from.
Example
A single artificial neuron might take three input values, multiply each by a learned weight, sum them with a bias, then apply an activation function to produce its output.
Common misconception
A single artificial neuron does not model anything close to a biological neuron's real complexity; the name is a loose analogy, not a biological equivalence.
Recall question
What three steps does a single artificial neuron perform on its inputs?
Keywords and related concepts
artificial neuronweighted sumneural networkactivation function