Training device and training method for neural network model
AssigneeIndustrial Technology Research Institute
InventorsMao-Yu Huang, Po-Yen Hsieh, Chih-Neng Liu, Tsann-Tay Tang
Life of this patent
Estimating the term…
Abstract
A training device and a training method for a neural network model. The training method includes: obtaining a data set; completing, according to the data set, a plurality of artificial intelligence (AI) model trainings to generate a plurality of models corresponding to the plurality of AI model trainings respectively; selecting, according to a first constraint, a first model set from the plurality of models; and selecting, according to a second constraint, the neural network model from the first model set.
Claims18
A training device for a neural network model, comprising:
- a transceiver;
- a storage medium, storing a plurality of modules;
- and
- a processor, coupled to the storage medium and the transceiver, and accessing and executing the plurality of modules, wherein the plurality of modules comprise:
- a data collection module, obtaining a data set through the transceiver;
- and
- a training module, completing a plurality of artificial intelligence (AI) model trainings according to the data set to generate a plurality of models corresponding to the plurality of AI model trainings respectively, selecting a first model set from the plurality of models according to a first constraint, and selecting the neural network model from the first model set according to a second constraint, wherein the first constraint is a first indicator of a confusion matrix and the second constraint is a second indicator of the confusion matrix, wherein the first constraint is different from the second constraint
- wherein the data collection module receives defect samples and normal samples through the transceiver and oversamples the defect samples to generate the data set in response to a ratio of the defect samples to the normal samples being less than a threshold.
A training method for a neural network model, comprising:
- obtaining a data set, comprising:
- receiving defect samples and normal samples and oversampling the defect samples to generate the data set in response to a ratio of the defect samples to the normal samples being less than a threshold;
- completing a plurality of artificial intelligence (AI) model trainings according to the data set to generate a plurality of models corresponding to the plurality of AI model trainings respectively;
- selecting a first model set from the plurality of models according to a first constraint;
- and
- selecting the neural network model from the first model set according to a second constraint,
- wherein the first constraint is a first indicator of a confusion matrix and the second constraint is a second indicator of the confusion matrix, wherein the first constraint is different from the second constraint.
Dependencies are inferred from the claim text.