Glossary

Quantisation

Representing a neural network's weights and activations with fewer bits, for example 8-bit integers, to cut memory and speed up inference on edge hardware, at a small cost in accuracy.

Learn it in depthDeployment, edge inference, FPGAs and robot safetyBudget control-loop latency, time a servo bus, quantise a model to INT8, pick an edge target, and add software and hardware safety limits to a learned policy.

Related terms

← All glossary terms