Computationally budgeted continual learning: What does matter?
A Prabhu, HA Al Kader Hammoud… - Proceedings of the …, 2023 - openaccess.thecvf.com
Continual Learning (CL) aims to sequentially train models on streams of incoming data that
vary in distribution by preserving previous knowledge while adapting to new data. Current …
vary in distribution by preserving previous knowledge while adapting to new data. Current …
Simple and scalable strategies to continually pre-train large language models
Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start
the process over again once new data becomes available. A much more efficient solution is …
the process over again once new data becomes available. A much more efficient solution is …
Maintaining plasticity via regenerative regularization
In continual learning, plasticity refers to the ability of an agent to quickly adapt to new
information. Neural networks are known to lose plasticity when processing non-stationary …
information. Neural networks are known to lose plasticity when processing non-stationary …
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 …
Continual learning as computationally constrained reinforcement learning
An agent that efficiently accumulates knowledge to develop increasingly sophisticated skills
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …
over a long lifetime could advance the frontier of artificial intelligence capabilities. The …
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL)
algorithms through the metric of online accuracy, which measures the accuracy of the model …
algorithms through the metric of online accuracy, which measures the accuracy of the model …
SIESTA: Efficient online continual learning with sleep
In supervised continual learning, a deep neural network (DNN) is updated with an ever-
growing data stream. Unlike the offline setting where data is shuffled, we cannot make any …
growing data stream. Unlike the offline setting where data is shuffled, we cannot make any …
Grasp: a rehearsal policy for efficient online continual learning
Continual learning (CL) in deep neural networks (DNNs) involves incrementally
accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is …
accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is …
[HTML][HTML] Artificial Intelligence Applications in Smart Healthcare: A Survey
The rapid development of AI technology in recent years has led to its widespread use in
daily life, where it plays an increasingly important role. In healthcare, AI has been integrated …
daily life, where it plays an increasingly important role. In healthcare, AI has been integrated …
From categories to classifier: Name-only continual learning by exploring the web
Continual Learning (CL) often relies on the availability of extensive annotated datasets, an
assumption that is unrealistically time-consuming and costly in practice. We explore a novel …
assumption that is unrealistically time-consuming and costly in practice. We explore a novel …