Catastrophic interference in connectionist networks

74 citations recorded by the source corpus.

How researchers see this paper

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

Reservoir computing approaches to recurrent neural network training (2009, background): “A notorious conundrum of neural network research is how to extend previously learned models by new items without impairing or destroying previously learned representations (catastrophic interference [32]).”
Self-Supervised Learning Aided Class-Incremental Lifelong Learning (2020, background): “Since continual acquisition of information from non-stationary data distributions generally leads to catastrophic forgetting [7, 29, 37], in which new knowledge overwrites old knowledge, leading to a”
Controlling Recurrent Neural Networks by Conceptors (2014, background): “Although a number of proposals have been made which partially alleviate the problem in special circumstances [32, 42], catastrophic forgetting was still listed”
Using Conceptors to Manage Neural Long-Term Memories for Temporal Patterns (2017, background): “…trained with backpropagation due to the “catastrophic forgetting” problem (appreciation in Douglas and Sejnowski (2008), partial solutions and further references in French (2003); Grossberg (2005); Goodrich and Arel (2014)) and for most associative memories (exception: Jiang et al. (2016)).”