Selecting artificial intelligence model based on input data
AssigneeSamsung Electronics Co., Ltd.
InventorsAnant BAIJAL, Vivek AGARWAL, Jayoon KOO
Life of this patent
Estimating the term…
Abstract
A method of selecting an artificial intelligence (AI) model based on input data to select an AI model capable of correctly obtaining a result corresponding to data to be classified, e.g., a classification result indicating one of at least one class, from among a plurality of AI models, and a display device for performing the method.
Claims20
A method of selecting an artificial intelligence model for classifying input data, the method comprising:
- obtaining first misclassified data of a first artificial intelligence model classifying data included in a training data set, the first misclassified data indicating first data of the training data set for which the first artificial intelligence model incorrectly classifies the first data;
- obtaining second misclassified data of a second artificial intelligence model classifying the data included in the training data set, the second misclassified data indicating second data of the training data set for which the second artificial intelligence model incorrectly classifies the second data;
- training a selection artificial intelligence model based on the first misclassified data and the second misclassified data;
- providing the input data to the selection artificial intelligence model;
- and
- selecting an optimal artificial intelligence model from among the first artificial intelligence model and the second artificial intelligence model to classify the input data, based on output of the selection artificial intelligence model.
A device for selecting an artificial intelligence model for classifying input data, the device comprising:
- a display;
- and
- a processor configured to execute at least one instruction to:
- obtain first misclassified data of a first artificial intelligence model classifying data included in a training data set, the first misclassified data indicating first data of the training data set for which the first artificial intelligence model incorrectly classifies the first data;
- obtain second misclassified data of a second artificial intelligence model classifying the data included in the training data set, the second misclassified data indicating second data of the training data set for which the second artificial intelligence model incorrectly classifies the second data;
- train a selection artificial intelligence model based on the first misclassified data and the second misclassified data;
- provide the input data to the selection artificial intelligence model;
- and
- select an optimal artificial intelligence model from among the first artificial intelligence model and the second artificial intelligence model to classify the input data, based on output of the selection artificial intelligence model.
A computer-readable recording medium having recorded thereon a computer program for executing a method of selecting an artificial intelligence model for classifying input data, the method comprising:
- obtaining first misclassified data of a first artificial intelligence model classifying data included in a training data set, the first misclassified data indicating first data of the training data set for which the first artificial intelligence model incorrectly classifies the first data;
- obtaining second misclassified data of a second artificial intelligence model classifying of the data included in the training data set, the second misclassified data indicating second data of the training data set for which the second artificial intelligence model incorrectly classifies the second data;
- training a selection artificial intelligence model based on the first misclassified data and the second misclassified data;
- providing the input data to the selection artificial intelligence model;
- and
- selecting an optimal artificial intelligence model from among the first artificial intelligence model and the second artificial intelligence model to classify the input data, based on output of the selection artificial intelligence model.
Dependencies are inferred from the claim text.