Back to results
US 2019/0057308 A1Published application
Method and device for pruning a neural network
AssigneesSK hynix Inc., Seoul National University R&Db Foundation
InventorsSeunghwan CHO, Sungjoo YOO, Youngjae JIN
Life of this patent
Estimating the term…
Abstract
A method for pruning a neural network includes initializing a plurality of threshold values respectively corresponding to a plurality of layers included in the neural network; selecting one of the plurality of layers; adjusting the threshold value of the selected layer; and adjusting a plurality of weights respectively corresponding to a plurality of synapses included in the neural network.
Claims18
A method for pruning a neural network, the method comprising:
- initializing a plurality of threshold values respectively corresponding to a plurality of layers included in the neural network;
- selecting one of the plurality of layers;
- adjusting the threshold value of the selected layer;
- and
- adjusting a plurality of weights respectively corresponding to a plurality of synapses included in the neural network.
2 more elements
A device for pruning a neural network, the device comprising:
- a computing circuit configured to perform a convolution operation including an addition operation and a multiplication operation;
- an input signal generator configured to generate input data, and to input the input data to the computing circuit;
- a threshold adjusting circuit configured to adjust a threshold value of a selected layer among a plurality of layers in the neural network;
- a weight adjusting circuit configured to adjust a plurality of weights of a plurality of synapses, respectively, which are included in the neural network;
- and
- a controller configured to prune the neural network by controlling the threshold adjusting circuit and the weight adjusting circuit.
3 more elements
Dependencies are inferred from the claim text.