Skip to content

Decoder

Definition
AI-generated

A decoder is the part of a neural network that maps internal states or latents to an output domain—reconstructed inputs in autoencoders, token logits in language models, or structured predictions.

Topics
LLM and Agents Machine learning concepts
Related
Autoencoder Cross-Attention Encoder

Why it matters in GWAS

Decoders drive sequence generation for protein or regulatory design, captioning models over plots, and some clinical report pipelines; sampling temperature and decoding policy affect reproducibility, so methods sections should specify decoding settings when LLM outputs feed curation or summaries.

Example usage

"The Decoder generated candidate regulatory DNA sequences conditioned on the GWAS fine-mapped SNP window embedding."

Autoencoder Cross-Attention Encoder KV Cache Large Language Model (LLM) Masked Attention Transformer Variational Autoencoder (VAE)
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Vaswani A, et al. (2017). Attention is all you need. NeurIPS.
← Decision Curve Analysis Decoy sequence →

Last updated (UTC · Git history)