Glossary term
Glossary term
Architecture
A probabilistic neural network that accounts for uncertainty in weights and outputs. A standard neural network regression model typically predicts a scalar value; for example, a standard model predicts a house price of 853,000. In contrast, a Bayesian neural network predicts a distribution of values; for example, a Bayesian model predicts a house price of 853,000 with a standard deviation of 67,200.
A Bayesian neural network relies on Bayes' Theorem to calculate uncertainties in weights and predictions. A Bayesian neural network can be useful when it is important to quantify uncertainty, such as in models related to pharmaceuticals. Bayesian neural networks can also help prevent overfitting.
Created for this library
A medical diagnostics startup uses a Bayesian neural network so each prediction comes with a calibrated uncertainty estimate for clinicians.
A self-driving team uses Bayesian neural networks for perception so the planner can downweight low-confidence detections.
A pharmaceutical research team uses a Bayesian neural network to predict drug binding affinity with uncertainty bounds that guide which candidates to test in the lab.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License