Seonglae ChoCognitive adjustment
An data that violates the expectations is more memorable for humans.
Inspired by this, a simple definition of surprise for a model can be its gradient with respect to the input. The larger the gradient is, the more different the input data is from the past data.
The key idea to train a long-term memory is to treat its training as an online learning problem, in which we aim to compress the past information into the parameters of long-term neural memory module
This surprise metric, however, can result in missing important information that comes after a big surprising moment. where is a data-dependent surprise decay and the term is controlling how much of momentary surprise should be incorporated into the final surprise metric in a data dependent manner.
How one can retrieve information from the memory?
arxiv.org
https://arxiv.org/pdf/2501.00663