G06V 10/778

Definition

Diese Klassifikationsstelle umfasst:

(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)

Techniques for active pattern learning for image or video recognition or understanding which dynamically adapt a learning algorithm (e.g. a neural network), either by interactively querying a supervisor (user) or from some other information source, like a teacher module, to classify or learn new data. Examples of techniques classified here include:

• Membership query synthesis, where the learner generates its own instance from an underlying data set. For example, if the dataset are pictures of humans and animals, the learner could send a clipped image of a leg to the teacher and query if this appendage belongs to an animal or human;
• Pool-based sampling, where instances are drawn from the entire data pool and assigned a confidence score, a measurement of how well the learner “understands” the data. The system then selects the instances for which it is the least confident and queries the teacher for the labels;
• Stream-based selective sampling, where unlabelled data samples are examined one at a time with the machine evaluating the informativeness of each item against its query parameters. The learner decides for itself whether to assign a label or query the teacher for each sample.

Examples

Active learning of weights and biases at different stages of a convolutional neural network for image classification

Querverweise

Informative Querverweise

Pattern recognition or machine learning, using clustering	G06V 10/762
Pattern recognition or machine learning, using classification	G06V 10/764
Pattern recognition or machine learning, using regression	G06V 10/766
Pattern recognition or machine learning, processing image features in feature spaces	G06V 10/77
Pattern recognition or machine learning, fusion	G06V 10/80
Digital computing; Complex mathematical operations	G06F 17/10
Machine learning in general	G06N 20/00

G06V 10/778

Definition Statement

This place covers:

Techniques for active pattern learning for image or video recognition or understanding which dynamically adapt a learning algorithm (e.g. a neural network), either by interactively querying a supervisor (user) or from some other information source, like a teacher module, to classify or learn new data. Examples of techniques classified here include:

• Membership query synthesis, where the learner generates its own instance from an underlying data set. For example, if the dataset are pictures of humans and animals, the learner could send a clipped image of a leg to the teacher and query if this appendage belongs to an animal or human;
• Pool-based sampling, where instances are drawn from the entire data pool and assigned a confidence score, a measurement of how well the learner “understands” the data. The system then selects the instances for which it is the least confident and queries the teacher for the labels;
• Stream-based selective sampling, where unlabelled data samples are examined one at a time with the machine evaluating the informativeness of each item against its query parameters. The learner decides for itself whether to assign a label or query the teacher for each sample.

Examples

Active learning of weights and biases at different stages of a convolutional neural network for image classification

References

Informative references

Pattern recognition or machine learning, using clustering	G06V 10/762
Pattern recognition or machine learning, using classification	G06V 10/764
Pattern recognition or machine learning, using regression	G06V 10/766
Pattern recognition or machine learning, processing image features in feature spaces	G06V 10/77
Pattern recognition or machine learning, fusion	G06V 10/80
Digital computing; Complex mathematical operations	G06F 17/10
Machine learning in general	G06N 20/00