Lifelong Machine Learning, Second Edition

By Zhiyuan Chen, B. Liu. 2018

172 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.

In Artificial Intelligence

Citations in the corpus

Incorporating neuro-inspired adaptability for continual learning in artificial intelligence (2023, neutral): “Specifically, to perform well on all tasks ever seen, a desirable solution should properly balance memory stability of old tasks with learning plasticity of new tasks, while being adequately compatible to capture their distributions (see Methods for details).”
Learngene: From Open-World to Your Learning Task (2021, background): “2018; Xu and Zhu 2018) is also referred to as lifelong learning (Chen and Liu 2018; Aljundi, Chakravarty, and Tuytelaars 2017; Chaudhry et al. 2019), which aims to continually learn over time by accommodating new knowledge while retaining previously learned experiences.”
Meta-Learning in Neural Networks: A Survey (2020, background): “Continual learning (CL) Continual or lifelong learning [60]–[62] refers to the ability to learn on a sequence of tasks drawn from a potentially non-stationary distribution, and in particular seek to do so while accelerating learning new tasks and without forgetting old tasks.”
DEMix Layers: Disentangling Domains for Modular Language Modeling (2021, background): “Continual Learning DEMIX-DAPT is a type of continual learning, in which the model learns incrementally on new data (Chen et al., 2018).”
Continual Contrastive Self-supervised Learning for Image Classification (2021, background): “Continual learning is also referred to as lifelong learning[13][1][9][37], sequential learning[4][43] or incremental learning[2][8][40][5].”
Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems (2019, background): “Zhang [16] presented a solution that can quickly adapt to new situations (e.”
DDGR: Continual Learning with Deep Diffusion-based Generative Replay (2023, background): “Continual learning (CL)—also referred to as lifelong learning (Chen & Liu, 2018), sequential learning (Aljundi et al., 2019), and incremental learning (Aljundi et al., 2018)—has emerged as an efficient way to mitigate catastrophic forgetting in deep learning models.”
Open-World Continual Learning: Unifying Novelty Detection and Continual Learning (2023, background): “This incremental learning function is called continual learning (CL) or lifelong learning [14].”
Jelly Bean World: A Testbed for Never-Ending Learning (2020, background): “Never-ending learning is in many respects similar to lifelong learning , also called continual learning (Chen & Liu, 2018).”
L2Explorer: A Lifelong Reinforcement Learning Assessment Environment (2022, background): “In the related, but broader, concept of Lifelong Learning (Chen and Liu 2018), an agent learns over a lifetime of experiences (see Fig.”
A Robustly Optimized BERT Pre-training Approach with Post-training (2021, methodology): “Inspired by (Chen and Liu, 2018; Sun et al., 2019) and (Parisi et al., 2019), which show Continual Learning can train the model with several tasks in sequence, but we ﬁnd that, standard Continual Learning method trains the model with only one task at each time with the demerit that it is easy to…”