US 2024/0193422 A1 · NEURON-BY-NEURON QUANTIZATION FOR EFFICIENT TRAINING OF LOW-BIT QUANTIZED NEURAL NETWORKS

Abstract

Quantization of a convolutional neural network (CNN) into a quantized neural network (QNN) reduces the computational resources required to operate the neural network, which is especially advantageous for operation of a neural network on resource-constrained devices. However, QNNs with low bit-widths suffer from significant losses in accuracies. Accordingly, approaches for quantization-aware training are disclosed that utilize component-by-component quantization during training to improve the accuracy of the resulting QNN. Component-by-component quantization may include filter-by-filter quantization, or preferably neuron-by-neuron quantization with some form of gradient forwarding.

Claims20

Dependent claims

A method of training a neural network comprising using at least one hardware processor to:

for each layer to be quantized in the neural network, for each of a plurality of iterations, until all of a plurality of components of the layer are quantized,
select a subset of the plurality of components, wherein each of the plurality of components comprises weights,
quantize the weights in the subset of components,
retrain the neural network, and
freeze the subset of components, such that the subset of components is not subsequently modified during training.

2 more elements

Dependencies are inferred from the claim text.

Neuron-by-neuron quantization for efficient training of low-bit quantized neural networks

Life of this patent

Neuron-by-neuron quantization for efficient training of low-bit quantized neural networks

Life of this patent

Abstract

Claims20