Accelerated Inference and Reduced Forgetting: The Dual Benefits of Early-Exit Networks in Continual Learning

arXiv:2403.07404v1 Announce Type: new
Abstract: Driven by the demand for energy-efficient employment of deep neural networks, early-exit methods have experienced a notable increase in research attention. These strategies allow for swift predictions by making decisions early in the network, thereby conserving computation time and resources. However, so far the early-exit networks have only been developed for stationary data distributions, which restricts their application in real-world scenarios with continuous non-stationary data. This study aims to explore the continual learning of the …

abstract arxiv attention benefits computation continual cs.ai cs.lg decisions demand employment energy exit however inference making network networks neural networks predictions research resources strategies swift type