liveBook · Manning

Neuron

As explained in Timeless Algorithms, The Foundational Ideas

A neuron is a computational unit in a neural network that combines inputs and produces an output.

A neuron transforms values received from the preceding layer. For inputs xᵢ, it computes a weighted sum, adds a bias, and applies an activation function: z = Σᵢ wᵢxᵢ + b; a = φ(z). The weights set each input’s influence, the bias shifts the response, and the activation introduces nonlinearity. section 11.2.1

Each neuron has its own weights, so neurons in the same layer can respond to different patterns. Its output becomes part of the next layer’s representation; during training, gradients guide adjustments to its weights and bias. section 11.2.1 section 11.2

Figure 11.1 A simplified feedforward neural network containing an input layer, two hidden layers, and an output layer. Information moves forward through weighted connections to produce a prediction. During training, error information moves backward so that the weights and biases can be adjusted. Modern deep networks typically contain many hidden layers and many nodes within each layer, producing millions or even billions of adjustable parameters. Despite that scale, they follow the same basic forward-and-backward process shown here.

The diagram situates individual nodes within connected layers and shows how their computations contribute to a prediction. section 11.2

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Defines weighted summation, bias, and activation, then connects node outputs to representations and training updates.
Examples
Uses pixel values, sensor readings, customer features, and word embeddings as examples of network inputs.
What it assumes
Assumes numerical values arrive from a preceding layer and defines how a neuron transforms them.
What you can do after
Understand how a neuron combines inputs and how its output contributes to a network prediction.
How it connects
Connects neurons to neural networks, weights, bias, activation functions, representations, and backpropagation.

Also explained in

Compare how 10 books explain neuron →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Timeless Algorithms, The Foundational Ideas. The section links point to the parts of the book it draws on.