Generative replay with feedback connections as a general strategy for continual learning
GM Van de Ven, AS Tolias - arXiv preprint arXiv:1809.10635, 2018 - arxiv.org
A major obstacle to developing artificial intelligence applications capable of true lifelong
learning is that artificial neural networks quickly or catastrophically forget previously learned …
learning is that artificial neural networks quickly or catastrophically forget previously learned …
Three scenarios for continual learning
GM Van de Ven, AS Tolias - arXiv preprint arXiv:1904.07734, 2019 - arxiv.org
Standard artificial neural networks suffer from the well-known issue of catastrophic
forgetting, making continual or lifelong learning difficult for machine learning. In recent years …
forgetting, making continual or lifelong learning difficult for machine learning. In recent years …
Brain-inspired replay for continual learning with artificial neural networks
Artificial neural networks suffer from catastrophic forgetting. Unlike humans, when these
networks are trained on something new, they rapidly forget what was learned before. In the …
networks are trained on something new, they rapidly forget what was learned before. In the …
Online continual learning with maximal interfered retrieval
Continual learning, the setting where a learning agent is faced with a never-ending stream
of data, continues to be a great challenge for modern machine learning systems. In …
of data, continues to be a great challenge for modern machine learning systems. In …
Distilled replay: Overcoming forgetting through synthetic samples
Abstract Replay strategies are Continual Learning techniques which mitigate catastrophic
forgetting by keeping a buffer of patterns from previous experiences, which are interleaved …
forgetting by keeping a buffer of patterns from previous experiences, which are interleaved …
Online class-incremental continual learning with adversarial shapley value
As image-based deep learning becomes pervasive on every device, from cell phones to
smart watches, there is a growing need to develop methods that continually learn from data …
smart watches, there is a growing need to develop methods that continually learn from data …
Retrospective adversarial replay for continual learning
Continual learning is an emerging research challenge in machine learning that addresses
the problem where models quickly fit the most recently trained-on data but suffer from …
the problem where models quickly fit the most recently trained-on data but suffer from …
Bns: Building network structures dynamically for continual learning
Continual learning (CL) of a sequence of tasks is often accompanied with the catastrophic
forgetting (CF) problem. Existing research has achieved remarkable results in overcoming …
forgetting (CF) problem. Existing research has achieved remarkable results in overcoming …
Loss decoupling for task-agnostic continual learning
YS Liang, WJ Li - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Continual learning requires the model to learn multiple tasks in a sequential order. To
perform continual learning, the model must possess the abilities to maintain performance on …
perform continual learning, the model must possess the abilities to maintain performance on …
Architecture matters in continual learning
A large body of research in continual learning is devoted to overcoming the catastrophic
forgetting of neural networks by designing new algorithms that are robust to the distribution …
forgetting of neural networks by designing new algorithms that are robust to the distribution …