Automatic hybrid quantization for deep neural network

A computer program product comprising a computer readable storage medium having stored thereon:

• program instructions programmed to obtain a target neural network structure and constraints for a target neural network;
• program instructions programmed to generate a meta learning network having an associated quantization function based, at least in part, on the target neural network structure;
• program instructions programmed to train the meta learning network based, at least in part, on providing a hybrid quantization vector as input to the meta learning network and providing a training dataset to the target neural network;
• program instructions programmed to obtain a plurality of hybrid quantization vectors;
• program instructions programmed to determine a new hybrid quantization vector from the plurality of hybrid quantization vectors;
• and
• program instructions programmed to retrain the trained meta learning network based, at least in part, on providing the new hybrid quantization vector as input to the trained meta learning network.

A computer system comprising:

• a processor set;
• and
• a computer readable storage medium;
• wherein:
• the processor set is structured, located, connected and programmed to run program instructions stored on the computer readable storage medium;
• and
• the stored program instructions include:
• program instructions programmed to obtain a target neural network structure and constraints for a target neural network;
• program instructions programmed to generate a meta learning network having an associated quantization function based, at least in part, on the target neural network structure;
• program instructions programmed to train the meta learning network based, at least in part, on providing a hybrid quantization vector as input to the meta learning network and providing a training dataset to the target neural network;
• program instructions programmed to obtain a plurality of hybrid quantization vectors;
• program instructions programmed to determine a new hybrid quantization vector from the plurality of hybrid quantization vectors;
• and
• program instructions programmed to retrain the trained meta learning network based, at least in part, on providing the new hybrid quantization vector as input to the trained meta learning network.