Catastrophic Interference in Connectionist Networks: Can It Be Predicted, Can It Be Prevented?

By R. M. French. 1993

How researchers see this paper

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

In Meta & Continual Learning

Citations in the corpus

Recurrent World Models Facilitate Policy Evolution (2018, background): “While the human brain can hold decades and even centuries of memories to some resolution [2], our neural networks trained with backpropagation have more limited capacity and suffer from issues such as catastrophic forgetting [16, 43, 69].”
iCaRL: Incremental Classifier and Representation Learning (2016, background): “…standard classification loss, which encourages improvements of the feature representation that allow classifying the newly observed classes well, it also contains the distillation loss, which ensures that the discriminative information learned previously is not lost during the new learning step.”
World Models (2018, background): “While the human brain can hold decades and even centuries of memories to some resolution (Bartol et al., 2015), our neural networks trained with backpropagation have more limited capacity and suffer from issues such as catastrophic forgetting (Ratcliff, 1990; French, 1994; Kirkpatrick et al., 2016).”
Continual Learning for Neural Machine Translation (2021, background): “However, continual learning remains a big challenge for artiﬁcial intelligence systems and models since they suffer from the problem of catastrophic forgetting (French, 1993), i.e., the learning of new tasks may cause the model to forget the knowledge learned from previous tasks.”
Revisiting Distillation and Incremental Classifier Learning (2018, background): “This led to preliminary work on incremental representation learning in the late 90s [1] [4] [5].”
A Strategy for an Uncompromising Incremental Learner (2017, methodology): “Catastrophic Forgetting : Early works by McCloskey, French and Robins outlines this issue [17, 1, 26].”