liveBook · Manning

Forward pass

As explained in Timeless Algorithms, The Foundational Ideas

The computation that propagates input data through a model to produce its output.

A forward pass carries an input through a neural network to produce a prediction. At each node, inputs are weighted, summed, and combined with a bias, then transformed by an activation function: z = Σᵢwᵢxᵢ + b; a = ϕ(z). Each layer passes its transformed values to the next. Weights and biases stay fixed during the pass, so prediction occurs without learning. section 11.2 section 11.2.2

The output depends on the task:

  • Regression produces a numerical prediction; binary classification produces a probability that can be compared with a decision threshold; multiclass classification produces probabilities for the possible classes. section 11.2

Pedestrian detection

A network transforms an observation into a 0.68 probability that a pedestrian is present. A threshold of 0.30 assigns the positive class and triggers braking; the forward pass itself changes no parameters. section 11.3.2

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.

Trace how information moves through network layers to produce a prediction; training also sends error information backward to adjust parameters. section 11.2

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Derives node calculations and traces layer transformations through task-specific outputs, stopping before parameter learning.
Examples
Uses regression and classification outputs, including a pedestrian-detection probability that crosses a braking threshold.
What it assumes
Assumes numerical inputs and network parameters, while defining how weighted sums, biases, and activation functions transform them.
What you can do after
Understand how fixed network parameters transform an input into a prediction and distinguish prediction from learning.
How it connects
Connects neural network layers and learned representations to activation functions, loss functions, backpropagation, and optimization.

Also explained in

Compare how 14 books explain forward pass →

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.