Online continual learning for embedded devices

TL Hayes, C Kanan - arxiv preprint arxiv:2203.10681, 2022 - arxiv.org
Real-time on-device continual learning is needed for new applications such as home robots,
user personalization on smartphones, and augmented/virtual reality headsets. However, this …

Automated identification of abnormal infant movements from smart phone videos

E Passmore, AL Kwong, S Greenstein… - PLOS digital …, 2024 - journals.plos.org
Cerebral palsy (CP) is the most common cause of physical disability during childhood,
occurring at a rate of 2.1 per 1000 live births. Early diagnosis is key to improving functional …

[PDF][PDF] Performance analysis of samplers and calibrators with various classifiers for asymmetric hydrological data

C Kaleeswari, K Kuppusamy… - International Journal of …, 2023 - researchgate.net
Asymmetric data classification presents a significant challenge in machine learning (ML).
While ML algorithms are known for their ability to classify symmetric data effectively …

A Continual Learning Method for Reducing Class Interference Based on Replay

Z Xu, T Wang, J Wang, C Li, Y Fu… - 2023 42nd Chinese …, 2023 - ieeexplore.ieee.org
Although deep neural networks perform well on many individual tasks, they suffer from
catastrophic forgetting when learning new tasks continually. Recently, various continual …

[PDF][PDF] Generalized Class Incremental Learning For Classifying Work Equipment

N de Rooij, MS Nobile, Y Zhang, P van Oostrum - research.tue.nl
Executive summary Employers in the Netherlands are obliged to have specific work
equipment inspected to guarantee a safe workplace based on the 'Arbobesluit'(Working …

Large-scale deep class-incremental learning

E Belouadah - 2021 - theses.hal.science
Incremental learning (IL) enables the adaptation of artificial agents to dynamic environments
in which data is presented in streams. This type of learning is needed when access to past …