Loss-error-aware quantization of a low-bit neural network

A tangible computer-readable storage medium comprising computer readable instructions which, when executed, cause at least one processor to implement at least:

• a network weight partitioner to partition unquantized network weights of a first deep neural network model into a first group of network weights to be quantized and a second group of network weights to be retrained;
• a loss calculator to process network weights of the first deep neural network model to calculate a first loss with respect to a loss function;
• a weight quantizer to quantize the first group of network weights to generate low-bit second network weights corresponding to the first group of network weights;
• the loss calculator to calculate a second loss of the low-bit second network weights with respect to the loss function and to determine a difference between the first loss and the second loss;
• a weight updater to update the second group of network weights based on the difference between the first loss and the second loss, the second group of network weights to be partitioned by the network weight partitioner to continue partitioning, quantizing, and retraining unquantized network weights;
• and
• a network model deployer to deploy a low-bit deep neural network model including the low-bit second network weights.

A computer-implemented method comprising:

• partitioning, using at least one processor, unquantized network weights of a first deep neural network model into a first group of network weights to be quantized and a second group of network weights to be retrained;
• processing, using the at least one processor, network weights of the first deep neural network model to calculate a first loss with respect to a loss function;
• quantizing, using the at least one processor, the first group of network weights to generate low-bit second network weights corresponding to the first group of network weights;
• calculating, using the at least one processor, a second loss of the second network weights with respect to the loss function to determine a difference between the first loss and the second loss;
• updating, using the at least one processor, the second group of network weights based on the difference between the first loss and the second loss, the second group of network weights to be partitioned using the at least one processor to continue partitioning, quantizing, and retraining unquantized network weights;
• and
• deploying, using the at least one processor, a low-bit deep neural network model including the low-bit second network weights.

An apparatus comprising:

• means for partitioning unquantized network weights of a first deep neural network model into a first group of network weights to be quantized and a second group of network weights to be retrained;
• means for processing network weights of the first deep neural network model to calculate a first loss with respect to a loss function;
• means for quantizing the first group of network weights to generate low-bit second network weights corresponding to the first group of network weights;
• means for calculating a second loss of the second network weights with respect to the loss function to determine a difference between the first loss and the second loss;
• means for updating the second group of network weights based on the difference between the first loss and the second loss, the second group of network weights to be partitioned by the means for partitioning to continue partitioning, quantizing, and retraining unquantized network weights;
• and
• means for deploying a low-bit deep neural network model including the low-bit second network weights.