Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning

5 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.

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference (2018, methodology): “This procedure closely follows recent enhancements discussed in (Zhang & Sutton, 2017; Riemer et al., 2017b;a) The sample function randomly samples k − 1 examples from the memory buffer M and interleaves them with the current example to form a single size k batch.”
Online Learned Continual Compression with Adaptive Quantization Modules (2019, background): “Most closely related to our work, Riemer et al. (2017) consider compressing memories for use in the continual classiﬁcation task.”
Online Learned Continual Compression with Stacked Quantization Module (2019, methodology): “Most closely related to our work Riemer et al. (2017) consider compressing memories for use in the continual classiﬁcation task.”
Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension (2019, methodology): “Several studies present methods to reduce forgetting with limited or no access to previous data (Riemer et al. 2017; Lopez-Paz and others 2017; Kirkpatrick et al. 2017; Serra et al. 2018; Riemer et al. 2018).”