Catastrophic forgetting in simple networks: an analysis of the pseudorehearsal solution.

By Marcus Frean, Anthony V. Robins. 1999

How researchers see this paper

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

Citations in the corpus

Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “Moreover, it has been suggested that humans perform a form of pseudo-replay or pseudo-rehearsals that is likely particularly active and useful for consolidation of knowledge during human sleep (Robins, 1995,9; Frean and Robins, 1999).”
Pareto-Based Multiobjective Machine Learning: An Overview and Case Studies (2008, background): “topic in machine learning, as well as in human memory systems, is the plasticity–stability tradeoff, which is also known as online learning [88], incremental learning [89], or catastrophic forgetting [ 90 ].”
Catastrophic Forgetting and the Pseudorehearsal Solution in Hopfield-type Networks (1998, methodology): “A number of studies have used MLP type networks (typically using back-propagation for training) to highlight the problem of CF and explore various issues (McCloskey and Cohen, 1989; Hetherington and Seidenberg, 1989; Ratcliff, 1990; Lewandowsky, 1991; Murre, 1992; French, 1992, 1994, 1997; McRae and”
Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods (2004, unknown): “In a different approach Robins [52] explored the links between CF and the popular theory that newly learned information is consolidated in the brain during sleep.”
Evolved Dual Weight Neural Architectures to Facilitate Incremental Learning (2009, methodology): “Past neural network approaches have been primarily concerned with memory tasks, rather than generalization tasks, and have tended to focus on minimizing catastrophic forgetting (Frean & Robins, 1999; French, 1999).”