Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting

By Bernard Ans, Stephane Rousset, R. M. French, Serban C. Musca. 2004

58 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience

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

Citations in the corpus

End-to-End Incremental Learning (2018, background): “However, learning models incrementally in this paradigm results in catastrophic forgetting , a phenomenon where the performance on the original (old) set of classes degrades dramatically [2,8,10,16– 18,22,23,30].”
Critical periods and catastrophic interference effects in the development of self-organizing feature maps. (2008, background): “…of simulation work exploring catastrophic interference effects has focused on errordriven learning systems such as back-propagation networks (Ans et al., 2004; French, 1991, 1992, 1999; French & Chater, 2002; Kortge, 1990; McCloskey & Cohen, 1989; Ratcliff, 1990; Robins, 1995; Robins &…”
Brain-Inspired Model for Incremental Learning Using a Few Examples (2020, background): “Essentially, classification accuracy rapidly decreases when learning new classes [2, 13, 15, 21, 24, 29].”
Online Task-free Continual Learning with Dynamic Sparse Distributed Memory (2022, background): “…in which the old information was transferred to a second, independent network and then inter-leaved with the new information being learned [16, 4], creating an approximation of the error surface of the previously learned patterns and integrating that error surface with the error surface…”
Continual Learning in Recurrent Neural Networks with Hypernetworks (2020, background): “[31] Bernard Ans, Stéphane Rousset, Robert M.”
Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods (2004, unknown): “Using Elman type networks pseudorehearsal based methods have also been shown to be effective at preserving learned sequences [3,4].”
Continual learning in recurrent neural networks (2020, background): “In an early work, Ans et al. (2004) proposed a secondary network that generates patterns for rehearsing previously learned information.”