Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods

36 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.

Deep Generative Dual Memory Network for Continual Learning (2017, background): “pseudopattern rehearsal (Robins, 1995; French, 1997; Robins, 2004) propose to preserve neural networks’ learnt mappings by arbitrarily sampling random inputs and their corresponding outputs from the neural networks and using them along with new task samples while training.”
Replay in Deep Learning: Current Approaches and Missing Biological Elements (2021, positive): “While the fast weights are used to learn new information, the slow weights can be used for generative replay (Robins, 1997, 2004).”
Neuron Clustering for Mitigating Catastrophic Forgetting in Supervised and Reinforcement Learning (2015, background): “Neural networks perform poorly at such tasks due to catastrophic forgetting, where learning to represent newly arrived information disrupts prior representation [28].”
Online Deep Learning: Growing RBM on the fly (2018, background): “Several studies have put forth online learning algorithms for training single layer perceptron networks [4, 12, 15].”