17843590. METHOD AND APPARATUS FOR META FEW-SHOT LEARNER simplified abstract (Samsung Electronics Co., Ltd.)
Contents
METHOD AND APPARATUS FOR META FEW-SHOT LEARNER
Organization Name
Inventor(s)
Timothy Hospedales of Staines (GB)
METHOD AND APPARATUS FOR META FEW-SHOT LEARNER - A simplified explanation of the abstract
This abstract first appeared for US patent application 17843590 titled 'METHOD AND APPARATUS FOR META FEW-SHOT LEARNER
Simplified Explanation
The present disclosure describes a computer-implemented method for training a machine learning meta learner classifier model to perform few-shot image or speech classification. The method involves iteratively obtaining a support set and a query set, adapting the model using the support set, measuring the performance of the adapted model using the query set, and updating the classifier based on the performance.
- The method involves training a machine learning meta learner classifier model.
- The model is trained iteratively by obtaining a support set and a query set.
- The model is adapted using the support set.
- The performance of the adapted model is measured using the query set.
- The classifier is updated based on the performance by minimizing the loss.
Potential applications of this technology:
- Few-shot image classification
- Few-shot speech classification
Problems solved by this technology:
- Addressing the challenge of few-shot classification tasks
- Improving the performance of machine learning models in few-shot scenarios
Benefits of this technology:
- Enables efficient training of machine learning models for few-shot classification tasks
- Improves the accuracy and performance of the models in few-shot scenarios
Original Abstract Submitted
The subject-matter of the present disclosure relates to a computer-implemented method of training a machine learning, ML, meta learner classifier model to perform few-shot image or speech classification, the method comprising: training the machine learning, ML, meta learner classifier model by: iteratively obtaining a support set and a query set of a current episode; adapting the model using the support set; measuring a performance of the adapted model using the query set; and updating the classifier based on the performance; wherein adapting the model using the support set comprises: deriving a Laplace approximated posterior using a linear classifier based on Gaussian mixture fitting; and deriving a predictive distribution using the approximated posterior; wherein measuring the performance of the adapted model using the query set comprises: determining a loss associated with the predictive distribution using the query set; and wherein updating the classifier based on the performance comprises minimising the loss.