AI engineering glossary · Time series recsys
What is Wide and Deep?
Wide and Deep (also called Wide & Deep): A recommendation architecture from Google that jointly trains a wide linear model, which memorises specific feature combinations, and a deep neural network, which generalises to unseen ones. Their outputs are added before the final prediction.
Wide and Deep: an example
Memorise 'installed app A then impressions of app B', while the deep part generalises to similar apps.
Related terms
More Time series recsys terms
- Additive decomposition
- Alternating least squares
- Anomaly detection (time series)
- ARCH model
- ARIMA
- ARIMAX
- ARMA
- Augmented Dickey-Fuller test
Where you learn it
Wide and Deep is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.