Abstract: Broadly speaking, the present techniques generally relate to machine learning models comprising neural network layers, in which the quantisation level of each layer of the model can be independently selected at run-time. In particular, the present application relates to a computer-implemented method for analysing input data on a device using a trained machine learning, ML, model, comprising independently selecting a quantisation level for each of a plurality of network layers of the model at runtime. The present application also relates to a computer-implemented method of training a machine learning model so that the quantisation level of each of the plurality of network layers is independently selectable at runtime. A single trained model with a single set of weights can therefore be deployed, with the quantisation of each layer selected at runtime to suit the capabilities of the device and available resource.

Abstract: Broadly speaking, the present techniques generally relate to machine learning models comprising neural network layers, in which the quantisation level of each layer of the model can be independently selected at run-time. In particular, the present application relates to a computer-implemented method for analysing input data on a device using a trained machine learning, ML, model, comprising independently selecting a quantisation level for each of a plurality of network layers of the model at runtime. The present application also relates to a computer-implemented method of training a machine learning model so that the quantisation level of each of the plurality of network layers is independently selectable at runtime. A single trained model with a single set of weights can therefore be deployed, with the quantisation of each layer selected at runtime to suit the capabilities of the device and available resource.