liveBook · Manning

Nonlinear mapping

As explained in Build AI Drug Discovery Pipelines

Nonlinearity is the property of a function or model in which outputs cannot be expressed as a linear transformation of inputs.

A nonlinear mapping produces outputs that cannot be represented as a linear transformation of its inputs. In a logistic model, the sigmoid transforms a weighted sum into a bounded, S-shaped probability between 0 and 1 while remaining differentiable for gradient-based learning. section 8.2.1

Nonlinearity changes what a model can represent, but a single logistic unit still has a linear decision boundary: inputs producing probability 0.5 lie on a hyperplane. Nonlinear feature transformations or hidden layers are needed to capture nonlinear relationships. section 8.2.1

In machine-learning workflows, nonlinear mappings support:

  • Transforming features into model inputs and improving a linear model with nonlinear transformations. section 3.0
  • Learning complex functions in graph neural networks by applying ReLU after graph-convolution layers; without nonlinearities, stacked linear layers collapse into one linear transformation. section 11.5.2

Sigmoid logistic model

Compute z = sum(x × w) + b, apply y = sigmoid(z), compare y with a target using binary cross-entropy, and backpropagate the loss to obtain gradients for the weights and bias.

Graph neural network branch

Apply ReLU after three graph-convolution layers, pool node representations into graph-level features, then pass them through fully connected layers to produce an embedding.

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains sigmoid behavior, decision-boundary limits, gradient compatibility, and ReLU-based graph-network construction, but stops short of formal theory.
Examples
Demonstrates sigmoid logistic regression in PyTorch and ReLU activation across molecular graph-convolution layers.
What it assumes
Assumes weighted sums and basic machine-learning models while introducing nonlinear transformations through logistic regression and graph-network examples.
What you can do after
Build it from scratch by applying sigmoid or ReLU activations and interpreting their effects on model expressiveness and learning.
How it connects
Connects nonlinear mappings to logistic regression, sigmoid functions, decision boundaries, hidden layers, activation functions, and graph neural networks.

Also explained in

Compare how 11 books explain nonlinear mapping →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.