LGCVNEMar 20, 2020

Online Continual Learning on Sequences

arXiv:2003.09114v135 citations
AI Analysis

This is an incremental summary of existing methods for agents and robots needing to learn from non-i.i.d. data streams.

The paper tackles the problem of catastrophic forgetting in online continual learning on sequential data, summarizing that models using experience replay typically outperform those without in incremental learning tasks.

Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples. Learning continually in a single data pass is crucial for agents and robots operating in changing environments and required to acquire, fine-tune, and transfer increasingly complex representations from non-i.i.d. input distributions. Machine learning models that address OCL must alleviate \textit{catastrophic forgetting} in which hidden representations are disrupted or completely overwritten when learning from streams of novel input. In this chapter, we summarize and discuss recent deep learning models that address OCL on sequential input through the use (and combination) of synaptic regularization, structural plasticity, and experience replay. Different implementations of replay have been proposed that alleviate catastrophic forgetting in connectionists architectures via the re-occurrence of (latent representations of) input sequences and that functionally resemble mechanisms of hippocampal replay in the mammalian brain. Empirical evidence shows that architectures endowed with experience replay typically outperform architectures without in (online) incremental learning tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes