Online Continual Learning on Sequences

By German Ignacio Parisi, Vincenzo Lomonaco. 2020

35 citations recorded by the source corpus.

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 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.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Pediatrics, Perinatology and Child Health

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Pediatrics, Perinatology and Child Health

Citations in the corpus

Online Continual Learning in Image Classification: An Empirical Survey (2021, background): “d stream of data, following the recent CL literature [17, 18, 27, 14].”
Continual Reinforcement Learning in 3D Non-stationary Environments (2019, background): “ is a hard challenge for current reinforcement learning systems. Recent works in this research area include meta-learning [12, 34, 1], hierarchical learning [49, 48] and continual learning approaches [21, 42, 36]. While both metalearning and hierarchical learning work around the idea of imposing som”
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (2020, methodology): “Online methods are based on streaming frameworks where learners are allowed to observe each example only once instead of iterating over a set of examples in a training session [28].”
Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks (2021, background): “The learning model needs to maintain a balance between plasticity (the ability to adapt to new knowledge) and stability (the ability to retain prior knowledge) [7], [8].”
Continual Learning for Affective Robotics: Why, What and How? (2020, methodology): “Hence, we argue that adopting CL as a learning paradigm, in particular using online CL methodologies [25], is crucial for affective robotics and HRI research.”