Efficient and accurate post-quantisation of artificial neural networks

A computerised system comprising:

• storage means storing labelled examples, as well as quantisation parameters and neural parameters of an artificial neural network, or ANN, wherein the neural parameters are parameters, which have been learned by training the ANN and quantised based on quantisation operations involving said quantisation parameters;
• and
• processing means, which are configured to
• instruct to load the quantisation parameters and the neural parameters of the ANN, and
• optimise the ANN by
• accessing labelled examples and executing the ANN on the labelled examples accessed, based on current neural parameters of the ANN to obtain inference results, in operation,
• optimising the quantisation parameters against an objective function computed according to the obtained inference results and labels of the labelled examples, while keeping at least some of the current neural parameters fixed, and
• updating the current neural parameters thanks to said quantisation operations, based on the optimised quantisation parameters.

A computer program product for optimising an artificial neural network, or ANN, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by processing means of a computerised system to cause the latter to:

• load quantisation parameters and neural parameters of the ANN, wherein the neural parameters include parameters, which have been learned by training the ANN and quantised based on quantisation operations involving said quantisation parameters;
• and
• optimise the ANN by
• accessing labelled examples and executing the ANN on the labelled examples accessed, based on current neural parameters of the ANN, to obtain inference results,
• optimising the quantisation parameters against an objective function computed according to the obtained inference results and labels of the labelled examples, while keeping at least some of the current neural parameters fixed, and
• updating the current neural parameters thanks to said quantisation operations, based on the optimised quantisation parameters.