Method and system for compressing application data for operations on multi-core systems

A method of image classification comprising:

• performing matrix factorization of a set of weights of a layer of a convolutional neural network image classification model to produce a decompression matrix and a set of factorized weights for the quantization;
• compressing the set of weights of by quantization of a floating point format of each weight to a floating point composite;
• storing the compressed set of weights and decompression matrix in a storage device of a multi-core device;
• determining an approximation of the weight values by decompressing the compressed weight matrix through the decompression matrix and expanding the floating point composite of each of the weight values;
• inputting features of an unknown image to the convolutional neural network image classification model;
• and
• executing the layer of the convolutional neural network model by a plurality of cores of the multi-core device with the approximation of weight values to produce an inference output classifying the unknown image.