Glossary term
Glossary term
Foundations
A model containing at least one hidden layer. A deep neural network is a type of neural network containing more than one hidden layer. For example, the following diagram shows a deep neural network containing two hidden layers.
Each neuron in a neural network connects to all of the nodes in the next layer. For example, in the preceding diagram, notice that each of the three neurons in the first hidden layer separately connect to both of the two neurons in the second hidden layer.
Neural networks implemented on computers are sometimes called artificial neural networks to differentiate them from neural networks found in brains and other nervous systems.
Some neural networks can mimic extremely complex nonlinear relationships between different features and the label.
See also convolutional neural network and recurrent neural network.
See Neural networks in Machine Learning Crash Course for more information.
Created for this library
A search-quality team uses a neural network ranker on top of a feature-engineered baseline for long-tail queries.
A medical imaging team uses a neural network on CT scans to flag suspicious nodules at higher sensitivity than the previous rules engine.
A startup uses a neural network on tabular features in its production scorer because it captures non-linear interactions well.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License