Deep class-incremental learning: A survey
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
A comprehensive survey of forgetting in deep learning beyond continual learning
Forgetting refers to the loss or deterioration of previously acquired information or knowledge.
While the existing surveys on forgetting have primarily focused on continual learning …
While the existing surveys on forgetting have primarily focused on continual learning …
A collective AI via lifelong learning and sharing at the edge
A Soltoggio, E Ben-Iwhiwhu, V Braverman… - Nature Machine …, 2024 - nature.com
One vision of a future artificial intelligence (AI) is where many separate units can learn
independently over a lifetime and share their knowledge with each other. The synergy …
independently over a lifetime and share their knowledge with each other. The synergy …
Class-incremental learning: A survey
Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
in many vision tasks in the closed world. However, novel classes emerge from time to time in …
Learning without forgetting for vision-language models
Class-Incremental Learning (CIL) or continual learning is a desired capability in the real
world, which requires a learning system to adapt to new tasks without forgetting former ones …
world, which requires a learning system to adapt to new tasks without forgetting former ones …
Continual learning: Applications and the road forward
Continual learning is a sub-field of machine learning, which aims to allow machine learning
models to continuously learn on new data, by accumulating knowledge without forgetting …
models to continuously learn on new data, by accumulating knowledge without forgetting …
Pilot: A pre-trained model-based continual learning toolbox
While traditional machine learning can effectively tackle a wide range of problems, it
primarily operates within a closed-world setting, which presents limitations when dealing …
primarily operates within a closed-world setting, which presents limitations when dealing …
Continual learning of large language models: A comprehensive survey
The recent success of large language models (LLMs) trained on static, pre-collected,
general datasets has sparked numerous research directions and applications. One such …
general datasets has sparked numerous research directions and applications. One such …
Overcoming Generic Knowledge Loss with Selective Parameter Update
Foundation models encompass an extensive knowledge base and offer remarkable
transferability. However this knowledge becomes outdated or insufficient over time. The …
transferability. However this knowledge becomes outdated or insufficient over time. The …
Cost-effective on-device continual learning over memory hierarchy with Miro
Continual learning (CL) trains NN models incrementally from a continuous stream of tasks.
To remember previously learned knowledge, prior studies store old samples over a memory …
To remember previously learned knowledge, prior studies store old samples over a memory …