Syntax and semantics for weight update compression of neural networks

Abstract

An example apparatus, method, and computer program product are provided. The apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode a high-level bitstream syntax for at least one neural network; wherein the high-level bitstream syntax comprises at least one information unit, wherein the at least one information unit comprises syntax definitions for the at least one neural network or a portion of the at least one neural network; and wherein a neural network representation (NNR) bitstream comprises one or more of the at least one information units, and wherein the syntax definitions provide one or more mechanisms for introducing a weight update compression interpretation into the NNR bitstream.

Dependencies are inferred from the claim text.