Neural-network building blocks · MLD-0450
Gated linear unit
A block multiplying one learned projection by a gate derived from another.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Control feature flow in a feed-forward block.
Original caveat
The gate's activation differs across GLU variants.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · Vision · NLP.
Aliases: GLU.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗