1)	Refining Representations: $D_{train}$ is put into memory such that the key-value pairs can represent $x_{test}$ better.

2)	Refining Parameters: the parameters of the embedding function of the testing set are refined.


University of Notre Dame

Learning with external memory first maps the training sample to a lower dimension space using the an embedding function, and save the mapped value and class labels as key-value pair to computers. For a given testing sample, it’s first transformed to the same low dimension space, and then the most similar key-value pairs in computer memory are extracted and combined to form a representation of this testing sample. Lastly, a simple prediction function is used to predict the class of this testing sample.

Learning with External Memory

Wang, Y., Yao, Q., Kwok, J. T., & Ni, L. M. (2020). Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3), 1-34.

Learn Before

Related