liveBook · Manning

Weighted sum

As explained in Timeless Algorithms, The Foundational Ideas

A linear combination is a sum of quantities multiplied by scalar coefficients.

A weighted sum multiplies input signals by scalar coefficients and adds the products. In a neural-network node, a bias is added before the result passes through an activation function. section 11.2

A hidden-node calculation

For input 2.0, a node with weight 0.8 and bias −0.5 produces 0.8 × 2.0 − 0.5 = 1.1, its pre-activation value. section 11.3.2

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Works through scalar pre-activation calculations and sigmoid transformations in a two-hidden-node example.
Examples
Uses input 2.0 with weight 0.8 and bias −0.5 to calculate a pre-activation value of 1.1.
What you can do after
Understand how an input, weight, and bias combine into a node’s pre-activation value.
How it connects
Connects weighted sums to neural networks, biases, activation functions, and forward propagation.

Also explained in

Compare how 5 books explain weighted sum →

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.