One-shot learning for the long term: consolidation with an artificial hippocampal algorithm
This work addresses the challenge of long-term knowledge retention in machine learning, particularly for continual learning scenarios, though it is an incremental step in the field.
The paper tackled the problem of catastrophic forgetting in few-shot learning by proposing an artificial hippocampal algorithm (AHA) to consolidate knowledge long-term, demonstrating that the system could learn in one-shot without forgetting previous concepts.
Standard few-shot experiments involve learning to efficiently match previously unseen samples by class. We claim that few-shot learning should be long term, assimilating knowledge for the future, without forgetting previous concepts. In the mammalian brain, the hippocampus is understood to play a significant role in this process, by learning rapidly and consolidating knowledge to the neocortex incrementally over a short period. In this research we tested whether an artificial hippocampal algorithm (AHA), could be used with a conventional Machine Learning (ML) model that learns incrementally analogous to the neocortex, to achieve one-shot learning both short and long term. The results demonstrated that with the addition of AHA, the system could learn in one-shot and consolidate the knowledge for the long term without catastrophic forgetting. This study is one of the first examples of using a CLS model of hippocampus to consolidate memories, and it constitutes a step toward few-shot continual learning.