Standard 4 stops to get here

GELU

Gaussian Error Linear Unit - a smooth activation function combining properties of dropout and ReLU, used in BERT and GPT.

Your route here

4 stops · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Neural Network ✓ understood

    A computational model inspired by biological neural networks, consisting of interconnected nodes (neurons) organized in layers that process information through weighted connections.

  3. Activation Function ✓ understood

    A non-linear function applied to neuron outputs that introduces non-linearity, enabling networks to learn complex patterns.

  4. ReLU ✓ understood

    Rectified Linear Unit - an activation function that outputs the input if positive, zero otherwise. f(x) = max(0, x).

  5. GELU · you are here ✓ understood

Gaussian Error Linear Unit - a smooth activation function combining properties of dropout and ReLU, used in BERT and GPT.

This concept is essential for understanding neural networks & deep learning and forms a key part of modern AI systems.

  • Activation Function
  • ReLU
  • Swish

Where it sits

Before this

ReLU
GELU

Leads to

Nothing yet: a destination in its own right.

Explore nearby

Neural Networks Swish A smooth activation function (x * sigmoid(x)) that often outperforms ReLU, discovered through neural architecture search. Neural Networks Mish A smooth, non-monotonic activation function (x * tanh(softplus(x))) providing better gradients than ReLU. Neural Networks ELU Exponential Linear Unit - an activation function that allows negative values, helping with vanishing gradients. Language & LLMs Transformer A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.