Model Training

Dropout

Randomly turning off some neurons during training so the AI doesn't over-memorize and can generalize better.

Definition

A regularization technique for neural networks that randomly deactivates a fraction of neurons on each training step, so the network cannot lean too heavily on any single neuron or path. This forces it to learn redundant, more general representations. Dropout is applied only during training; at inference all neurons are active, with their outputs scaled to compensate.

Why it matters

Dropout is one of the simplest and most effective defenses against overfitting, where a model memorizes its training data but fails on new inputs. It costs almost nothing to add and routinely improves how well a model generalizes to the real world.

Related terms in Model Training

Adversarial Training

Teaching an AI to defend itself by constantly attacking it with tricky or malicious inputs during training.

Autoencoders

A neural network that learns to compress data into a small code and then unzip it back to the original.

Distillation (Model Distillation)

Teaching a small, fast AI model to mimic a large, expensive one, so you get similar results at a fraction of the cost.

Epoch

One complete pass through the entire training dataset, the AI sees every example once per epoch.

Back to the full glossary

From vocabulary to outcomes

Ready to put Dropout to work?

Knowing the term is step one. Deploying it inside a revenue architecture that compounds is what Sophizo builds.

Book a Discovery Call