AI engineering glossary · Deep learning core
What is neural network pruning?
Neural network pruning (also called Weight pruning): The removal of weights, neurons or whole channels that contribute little, usually followed by fine-tuning. It shrinks model size and can speed up inference with a modest loss in accuracy.
Neural network pruning: an example
Removing the 50 percent smallest-magnitude weights of a layer and retraining briefly can leave accuracy nearly unchanged.
Related terms
More Deep learning core terms
- Neural tangent kernel
- Neuron
- One-cycle policy
- Optimiser
- Orthogonal initialisation
- Output layer
- Parametric ReLU
- Recurrent neural network
Where you learn it
Neural network pruning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.