Skip to content

Backpropagation

Definition
AI-generated

Backpropagation is the algorithm that computes gradients of a loss with respect to all neural network weights by applying the chain rule backward through the computation graph, enabling efficient gradient descent training of deep models.

Topics
LLM and Agents
Synonyms
Backprop
Related
Deep Learning Gradient Descent Loss Function

Why it matters in GWAS

Backpropagation underpins essentially all modern deep learning used in genomics—from sequence predictors to single-cell models—so reported performance depends on optimization details, regularization, and data splits as much as on architecture.

Example usage

"The variant scorer was a 20-layer ResNet-style CNN trained with Adam and standard backpropagation on windows around ClinVar sites."

Deep Learning Gradient Descent Loss Function Machine Learning Optimizer Multilayer Perceptron (MLP) Neural Network
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

  • Rumelhart DE, Hinton GE, Williams RJ. (1986). Learning representations by back-propagating errors. Nature.
← Backcross Bacterial artificial chromosome (BAC) →

Last updated (UTC · Git history)