Chapter 4

Activations and Nonlinearity

Activation functions, ReLU, sigmoid, tanh, saturation, hidden-unit detectors, and why depth needs nonlinear transforms.

What this chapter does

Activations are what let depth matter. This chapter shows how nonlinear transforms bend linear scores, how ReLU and bounded activations behave, and why stacked linear maps need activations between them.

Lessons

Read these in order.

Start with the chapter introduction, then move through the topic lessons. The order is chosen so each page can reuse ideas from the pages before it.

  1. 01
    Introduction

    Why nonlinear activations belong between linear model pieces.

  2. 02
    What Activation Functions Do

    Pre-activations, activation outputs, and the role of nonlinear transforms.

  3. 03
    ReLU

    The simple max(0, x) activation and why its bend matters.

  4. 04
    Sigmoid and Tanh

    Bounded nonlinearities, historical context, and why their ranges matter.

  5. 05
    Saturation

    Flat activation regions and why they can weaken gradient signals.

  6. 06
    Piecewise-Linear Behavior

    How ReLU networks build richer functions from straight pieces.

  7. 07
    Hidden Units as Detectors

    Reading hidden units as weighted evidence plus nonlinear response.

  8. 08
    Why Stacked Linear Maps Need Nonlinearity

    Why depth only becomes expressive when activations interrupt linear maps.

Before moving on

  • Compute ReLU and identify activation outputs.
  • Explain sigmoid, tanh, and saturation.
  • Read hidden units as detector-like computations.
  • Explain why stacked linear layers need nonlinear activations.

Where this leads

  • Multilayer Perceptrons
  • Backpropagation Through Networks
  • Training stability

Chapter progress