Skip to content

Loss Function

Definition
AI-generated

A loss function (objective) scores how far model predictions are from targets or surrogate constraints during training—e.g. cross-entropy for classification, mean squared error for regression, or contrastive losses for embeddings—so gradient-based optimizers can update parameters.

Topics
LLM and Agents Machine learning concepts
Related
Backpropagation Cross-Validation Deep Learning

Why it matters in GWAS

Neural predictors of disease or molecular endpoints inherit the loss’s implicit assumptions; class imbalance, relatedness, or population structure may require weighted losses or mixed-model baselines that GWAS practitioners prefer for interpretability.

Example usage

"Loss Function appears in the methods to support interpretation of the primary results."

Backpropagation Cross-Validation Deep Learning Genome-Wide Association Study (GWAS) Gradient Descent Machine Learning Neural Network Optimizer
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

  • Goodfellow I, Bengio Y, Courville A. (2016). Deep Learning. MIT Press.
← Long Short-Term Memory (LSTM) Loss-of-Function Variant →

Last updated (UTC · Git history)