公开(公告)号：US20220027715A1

公开(公告)日：2022-01-27

申请号：US17383132

申请日：2021-07-22

Applicant: STMICROELECTRONICS S.r.l.

Inventor： Diego CARRERA ,  Matteo COLELLA ,  Giuseppe DESOLI ,  Giacomo BORACCHI ,  Beatrice ROSSI ,  Pasqualina FRAGNETO ,  Luca FRITTOLI

IPC: G06N3/063 ,  G06N3/04 ,  G06K9/62

Abstract: A method, comprising: providing an ANN processing stage having a plurality of processing layers with respective parameters including at least one set of weight parameters, at least one input, resp. output, activation parameter and at least one activation function parameter; setting to an integer value a dimensional parameter of a lattice having a plurality of lattice points and identified by a set of basis vectors; selecting a set of weight parameters of a respective processing layer; vectorizing the selected set of weight parameters producing a set of weight vectors arranged as items of a matrix of weight vectors; normalizing the matrix of weight vectors; applying lattice vector quantization, LVQ, processing to the matrix of normalized weight vectors, producing a codebook of codewords; indexing by encoding codewords of the codebook as a function of the lattice, producing respective tuples of indices. The normalization comprises solving an optimization problem having a first term configured to provide normalized weight values approximating at least output, as a function of at least one input, activation parameter, and a regularization term ΩL, configured to amplify weight values having a short distance from the lattice points of the lattice L.