Avoiding catastrophic forgetting by coupling two reverberating neural networks

How researchers see this paper

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

Revisiting Distillation and Incremental Classifier Learning (2018, background): “This led to preliminary work on incremental representation learning in the late 90s [6] [7] [8].”
A Continual Learning Survey: Defying Forgetting in Classification Tasks (2019, background): “replaying samples or virtual samples from the past [8], [35] or introducing dual architectures [36], [37], [38].”
Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods (2004, methodology): “Since the method was proposed there have been a range of studies based on or related to it, including [1, 2, 3, 4, 16, 19, 20, 22, 23, 24, 38, 42, 52, 53, 54, 55, 56, 57, 58, 59, 65, 66].”