All terms

Dropout

A regularization technique that randomly disables neurons during training to reduce overfitting.

Deep Learning1 min read

Definition

During training, dropout sets a fraction of activations to zero at random each step, forcing the network not to rely on any single pathway. At inference, all units are active (with scaling).

Related ideas appear as DropPath / stochastic depth in modern architectures.

In simple terms

If teammates randomly sit out of practice, everyone must learn the play — the team cannot depend on one star player.

Where you see it

  • Classic MLPs and CNNs with dropout layers.
  • Transformers often use attention/residual dropout.

How it works

  1. 1.Sample a mask

    Randomly zero activations with probability p.

  2. 2.Forward and backprop

    Train on the thinned network.

  3. 3.Disable at inference

    Use the full network for predictions.

Why it matters

  • Dropout is a simple, effective defense against overfitting in deep nets.

Often confused

  • More dropout is always better.

    Too much dropout underfits; tune it like any hyperparameter.