Dual-Memory Deep Learning Architectures for Lifelong Learning of Everyday Human Behaviors

44 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.

Continual Learning by Asymmetric Loss Approximation With Single-Side Overestimation (2019, background): “The approaches in this category realize continual learning by freezing model parameters learned from the previous tasks and/or providing limited architectural variations for learning the new tasks [30, 22, 3, 20].”
Toward Continual Learning for Conversational Agents (2017, background): “(Rusu et al., 2016; Lee et al., 2016).”
Incremental Lifelong Deep Learning for Autonomous Vehicles (2018, background): “Some techniques involve specially designed neural networks such as dual-memory architectures that combine different networks for modelling fast and slow memory [7], and dynamicallyexpandable networks that add new neurons on the fly to accommodate new tasks [8].”
Online Deep Learning: Learning Deep Neural Networks on the Fly (2017, background): “There have been attempts at making deep learning compatible with online learning (Zhou, Sohn, and Lee 2012; Lee et al. 2016) and (Lee et al. 2017).”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “They abandon the memory modules in [445] and”
Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability (2019, background): “proposed a dual memory architecture that process slow-changing global patterns [27]; Zhou et al.”