Adapters for quantization
AssigneeQUALCOMM Incorporated
InventorsMinseop PARK, Jaeseong YOU, Simyung CHANG, Markus NAGEL, Chirag Sureshbhai PATEL
Life of this patent
Estimating the term…
Abstract
A processor-implemented method for adaptive quantization in an artificial neural network (ANN) includes receiving an ANN model. The ANN model has multiple channels of target activations. A quantization module is incorporated between a first linear layer of the ANN and a second linear layer of the ANN to generate an adapted ANN. The quantization module scales a first set of weights and biases of the first linear layer based on a learnable quantization module parameter and scales a second set of weights of the second linear layer based on an inverse of the learnable quantization module parameter.
Claims28
A processor-implemented method, comprising:
- receiving an artificial neural network (ANN) model, the ANN model having a plurality of channels of target activations;
- and
- incorporating a quantization module between a first linear layer of the ANN model and a second linear layer of the ANN model to generate an adapted ANN model, the quantization module scaling a first set of weights and biases of the first linear layer based on a learnable quantization module parameter and scaling a second set of weights of the second linear layer based on an inverse of the learnable quantization module parameter.
An apparatus, comprising:
- a memory;
- and
- at least one processor coupled to the memory, the at least one processor configured:
- to receive an artificial neural network (ANN) model, the ANN model having a plurality of channels of target activations;
- and
- to incorporate a quantization module between a first linear layer of the ANN and a second linear layer of the ANN model to generate an adapted ANN model, the quantization module scaling a first set of weights and biases of the first linear layer based on a learnable quantization module parameter and scaling a second set of weights of the second linear layer based on an inverse of the learnable quantization module parameter.
A non-transitory computer-readable medium having program code recorded thereon, the program code executed by a processor and comprising:
- program code to receive an artificial neural network (ANN) model, the ANN model having a plurality of channels of target activations;
- and
- program code to incorporate a quantization module between a first linear layer of the ANN model and a second linear layer of the ANN model to generate an adapted ANN model, the quantization module scaling a first set of weights and biases of the first linear layer based on a learnable quantization module parameter and scaling a second set of weights of the second linear layer based on an inverse of the learnable quantization module parameter.
An apparatus, comprising:
- means for receiving an artificial neural network (ANN) model, the ANN model having a plurality of channels of target activations;
- and
- means for incorporating a quantization module between a first linear layer of the ANN model and a second linear layer of the ANN model to generate an adapted ANN model, the quantization module scaling a first set of weights and biases of the first linear layer based on a learnable quantization module parameter and scaling a second set of weights of the second linear layer based on an inverse of the learnable quantization module parameter.
Dependencies are inferred from the claim text.