A Study on Catastrophic Forgetting in Deep LSTM Networks

35 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.

Online Continual Learning in Image Classification: An Empirical Survey (2021, background): “Recent works have confirmed that RNNs, including LSTMs, are also immensely affected by CF [132, 133, 134].”
Class-Incremental Learning: Survey and Performance Evaluation on Image Classification (2020, background): “Only recently the impact of catastrophic forgetting in recurrent LSTM networks was studied [90].”
Continual Learning with Gated Incremental Memories for sequential data processing (2020, methodology): “Table I and Figure 4 show that, in accordance with the results presented in [24], LSTM and LMN models suffer from catastrophic forgetting of old subtasks, independently”
Continual Learning in Recurrent Neural Networks with Hypernetworks (2020, background): “[5] Monika Schak and Alexander Gepperth.”
Continual learning in recurrent neural networks (2020, background): “However, CL for sequential data has only received little attention, despite recent work confirming that recurrent neural networks (RNNs) also suffer from catastrophic forgetting (Schak and Gepperth, 2019).”