Back to results
US 12,755,191 B2Granted
Training device to learn data and generate a model calculating an anomaly score, training method, and training program
AssigneeNTT, Inc.
InventorYuki Yamanaka
Life of this patent
Estimating the term…
Abstract
A generation unit learns data selected as unlearned data among learning data and generates a model calculating an anomaly score. A selection unit selects, as unlearned data, at least some of data in which an anomaly score calculated by the model generated by the generation unit is equal to or greater than a threshold among the learning data.
Claims13
A training device comprising:
- processing circuitry configured to:
- learn data selected as unlearned data among learning data and generate a model calculating an anomaly score, wherein the model is a Variational Auto Encoder (VAE) that is used to learn the data and is used for the calculating of the anomaly score;
- and
- select, as the unlearned data, at least some of data in which an anomaly score calculated by the model is equal to or greater than a threshold among the learning data,
- wherein the threshold is determined based on a loss value obtained in generation of the model, and the threshold is calculated based on an average or a variance of the loss value.
2 more elements
A training method executed by a training device, the method comprising:
- learning data selected as unlearned data among learning data and generating a model calculating an anomaly score, wherein the model is a Variational Auto Encoder (VAE) that is used to learn the data and is used for the calculating of the anomaly score;
- and
- selecting, as the unlearned data, at least some of data in which an anomaly score calculated by the model is equal to or greater than a threshold among the learning data,
- wherein the threshold is determined based on a loss value obtained in generation of the model, and the threshold is calculated based on an average or a variance of the loss value.
1 more element
A non-transitory computer-readable recording medium storing therein a training program that causes a computer to execute a process comprising:
- learning data selected as unlearned data among learning data and generating a model calculating an anomaly score, wherein the model is a Variational Auto Encoder (VAE) that is used to learn the data and is used for the calculating of the anomaly score;
- and
- selecting, as the unlearned data, at least some of data in which an anomaly score calculated by the model is equal to or greater than a threshold among the learning data,
- wherein the threshold is determined based on a loss value obtained in generation of the model, and the threshold is calculated based on an average or a variance of the loss value.
1 more element
Dependencies are inferred from the claim text.