liveBook · Manning

Model weight

As explained in Timeless Algorithms, The Foundational Ideas

A learned numerical coefficient that controls an input’s contribution in a neural network.

A weight is an adjustable numerical coefficient that controls how strongly an input contributes to a calculation. In a neural network, each node uses weights to combine incoming values; the node then adds a bias and applies an activation function. section 11.2.1

A weight’s value shapes the influence of its input:

  • A large positive weight increases that input’s influence in one direction; a negative weight reverses its influence; a weight near zero gives it little influence. section 11.2.1
  • During training, backpropagation computes the loss gradient with respect to each weight, and an optimization algorithm uses the gradients to update the weights. section 11.2
f(x)=wTx+b

In a linear decision function, the weight vector multiplies the input features; its components set their contributions, while the bias shifts the boundary. section 8.2.1

From image patterns to representations

In an image network, weights help determine how inputs contribute to layer responses. Layers can represent simple visual patterns and combine them into shapes and objects. section 11.2.1

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Explains weight signs, magnitudes, geometric effects in a classifier, and gradient-based updates, without deriving the optimization procedure.
Examples
Uses transformed temperature features in a classifier and visual patterns in an image network.
What you can do after
Understand how weight values shape input influence and how training adjusts them using loss gradients.
How it connects
Connects weights to neural networks, bias, activation functions, backpropagation, optimization, and decision boundaries.

Also explained in

Compare how 8 books explain model weight →

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.