# Ridge regression and the multilayer perceptron

Source: https://onco.cc/terms/ridge-regression/  
OnCo record `ridge-regression` (Term). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Ridge regression is linear regression with a penalty that shrinks coefficients, which keeps it stable when there are more genes than samples; a multilayer perceptron is the simplest neural network, a few fully connected layers.

## Summary

Ridge regression estimates multiple-regression coefficients when the variables are highly correlated, by adding an L2 penalty (Wikipedia); with twenty thousand correlated genes and a few hundred samples it is the natural per-drug or per-outcome head on top of principal components. A multilayer perceptron is a feedforward network of fully connected layers with non-linear activations (Wikipedia), the usual encoder in autoencoders and the usual non-linear baseline; when it does not beat ridge, the non-linearity is not buying anything.

## Fields

- Kind: Term
- Last checked: 2026-09-24
- Also known as: ridge regression; L2 regularisation; L2-regularised regression; ridge head; multilayer perceptron; MLP; feedforward network; MLP head
- Tags: cansim-terms

## Notes

- Listed in the CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme; CanSim page path /terms/ridge-regression.

## Sources

- Wikipedia: https://en.wikipedia.org/wiki/Ridge_regression
- Wikipedia: multilayer perceptron: https://en.wikipedia.org/wiki/Multilayer_perceptron
- Wikipedia: https://en.wikipedia.org/wiki/Ridge_regression

## Connected records

- terms: [Cancer AI vocabulary (CanSim terms map)](https://onco.cc/terms/cancer-ai-vocabulary/), [Drug-response baselines and frameworks: mean-drug floor, LightGBM, DrEval, IMPROVE, DeepTTA](https://onco.cc/terms/drug-response-baselines/), [Linear probe](https://onco.cc/terms/linear-probe/), [Logistic regression and nearest-centroid classifiers](https://onco.cc/terms/logistic-regression-term/), [Loss functions: cross-entropy and mean squared error](https://onco.cc/terms/cross-entropy-mse/), [Principal component analysis (PCA) as a feature compressor](https://onco.cc/terms/pca/)

---
JSON: https://onco.cc/api/v1/entities/ridge-regression.json