English
Related papers

Related papers: Train-On-Request: An On-Device Continual Learning …

200 papers

Brain-machine interfaces (BMIs) have emerged as a transformative force in assistive technologies, empowering individuals with motor impairments by enabling device control and facilitating functional recovery. However, the persistent…

Signal Processing · Electrical Eng. & Systems 2024-03-28 Xiaying Wang , Lan Mei , Victor Kartsch , Andrea Cossettini , Luca Benini

Human Activity Recognition (HAR) is an attractive topic to perceive human behavior and supplying assistive services. Besides the classical inertial unit and vision-based HAR methods, new sensing technologies, such as ultrasound and…

Human-Computer Interaction · Computer Science 2024-07-08 Pixi Kang , Julian Moosmann , Sizhen Bian , Michele Magno

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Haoran Chen , Micah Goldblum , Zuxuan Wu , Yu-Gang Jiang

Photonic computing has emerged as a promising solution for accelerating computation-intensive artificial intelligence (AI) workloads, offering unparalleled speed and energy efficiency, especially in resource-limited, latency-sensitive edge…

Emerging Technologies · Computer Science 2024-06-04 Haotian Lu , Sanmitra Banerjee , Jiaqi Gu

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers…

Human-Computer Interaction · Computer Science 2022-11-15 Dongrui Wu , Yifan Xu , Bao-Liang Lu

The performance of neural decoders can degrade over time due to nonstationarities in the relationship between neuronal activity and behavior. In this case, brain-machine interfaces (BMI) require adaptation of their decoders to maintain high…

Machine Learning · Computer Science 2012-06-19 Tayfun Gürel , Carsten Mehring

Large Language Models (LLMs) are revolutionizing the AI industry with their superior capabilities. Training these models requires large-scale GPU clusters and significant computing time, leading to frequent failures that significantly…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-10 Ning Lu , Qian Xie , Hao Zhang , Wenyi Fang , Yang Zheng , Zheng Hu , Jiantao Ma

On-device training is essential for neural networks (NNs) to continuously adapt to new online data, but can be time-consuming due to the device's limited computing power. To speed up on-device training, existing schemes select trainable NN…

Machine Learning · Computer Science 2023-12-25 Kai Huang , Boyuan Yang , Wei Gao

Electroencephalogram (EEG)-based Brain-Computer Interfaces (BCIs) have garnered significant interest across various domains, including rehabilitation and robotics. Despite advancements in neural network-based EEG decoding, maintaining…

Signal Processing · Electrical Eng. & Systems 2024-09-04 Sizhen Bian , Pixi Kang , Julian Moosmann , Mengxi Liu , Pietro Bonazzi , Roman Rosipal , Michele Magno

Transfer learning (TL) has been widely used in motor imagery (MI) based brain-computer interfaces (BCIs) to reduce the calibration effort for a new subject, and demonstrated promising performance. While a closed-loop MI-based BCI system,…

Signal Processing · Electrical Eng. & Systems 2023-05-04 Dongrui Wu , Xue Jiang , Ruimin Peng , Wanzeng Kong , Jian Huang , Zhigang Zeng

On-device recommender systems recently have garnered increasing attention due to their advantages of providing prompt response and securing privacy. To stay current with evolving user interests, cloud-based recommender systems are…

Information Retrieval · Computer Science 2023-08-25 Xin Xia , Junliang Yu , Guandong Xu , Hongzhi Yin

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 setting poses unique challenges: embedded devices have…

Machine Learning · Computer Science 2022-07-18 Tyler L. Hayes , Christopher Kanan

Ordinal regression is commonly formulated as a multi-class problem with ordinal constraints. The challenge of designing accurate classifiers for ordinal regression generally increases with the number of classes involved, due to the large…

Machine Learning · Computer Science 2015-03-18 Chun-Wei Seah , Ivor W. Tsang , Yew-Soon Ong

On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. Users can benefit from customized AI models without having to transfer the data to the cloud, protecting the privacy.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Ji Lin , Ligeng Zhu , Wei-Ming Chen , Wei-Chen Wang , Chuang Gan , Song Han

Driven by the progress in efficient embedded processing, there is an accelerating trend toward running machine learning models directly on wearable Brain-Machine Interfaces (BMIs) to improve portability and privacy and maximize battery…

Signal Processing · Electrical Eng. & Systems 2024-09-18 Lan Mei , Thorir Mar Ingolfsson , Cristian Cioflan , Victor Kartsch , Andrea Cossettini , Xiaying Wang , Luca Benini

The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under…

Machine Learning · Computer Science 2024-04-23 Sibo Gai , Donglin Wang , Li He

Cognitive functions in current artificial intelligence networks are tied to the exponential increase in network scale, whereas the human brain can continuously learn hundreds of cognitive functions with remarkably low energy consumption.…

Artificial Intelligence · Computer Science 2025-04-09 Bing Han , Feifei Zhao , Yinqian Sun , Wenxuan Pan , Yi Zeng

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge…

Machine Learning · Computer Science 2026-04-21 Xiao Ma , Young D. Kwon , Dong Ma

Health monitoring applications increasingly rely on machine learning techniques to learn end-user physiological and behavioral patterns in everyday settings. Considering the significant role of wearable devices in monitoring human body…

Machine Learning · Computer Science 2022-08-03 Sina Shahhosseini , Yang Ni , Hamidreza Alikhani , Emad Kasaeyan Naeini , Mohsen Imani , Nikil Dutt , Amir M. Rahmani

On-device training for personalized learning is a challenging research problem. Being able to quickly adapt deep prediction models at the edge is necessary to better suit personal user needs. However, adaptation on the edge poses some…

Machine Learning · Computer Science 2021-05-28 Lorenzo Pellegrini , Vincenzo Lomonaco , Gabriele Graffieti , Davide Maltoni
‹ Prev 1 2 3 10 Next ›