All one needs to know about metaverse: A complete survey on technological singularity, virtual ecosystem, and research agenda
Since the popularisation of the Internet in the 1990s, the cyberspace has kept evolving. We
have created various computer-mediated virtual environments including social networks …
have created various computer-mediated virtual environments including social networks …
On-device deep learning for mobile and wearable sensing applications: A review
OD Incel, SÖ Bursa - IEEE Sensors Journal, 2023 - ieeexplore.ieee.org
Although running deep-learning (DL) algorithms is challenging due to resource constraints
on mobile and wearable devices, they provide performance improvements compared to …
on mobile and wearable devices, they provide performance improvements compared to …
[HTML][HTML] The social shaping of the metaverse as an alternative to the imaginaries of data-driven smart Cities: A study in science, technology, and society
SE Bibri - Smart Cities, 2022 - mdpi.com
Science and technology transform the frontiers of knowledge and have deep and powerful
impacts on society, demonstrating how social reality varies with each era of the world. As a …
impacts on society, demonstrating how social reality varies with each era of the world. As a …
Design principles for lifelong learning AI accelerators
Lifelong learning—an agent's ability to learn throughout its lifetime—is a hallmark of
biological learning systems and a central challenge for artificial intelligence (AI). The …
biological learning systems and a central challenge for artificial intelligence (AI). 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 …
Yono: Modeling multiple heterogeneous neural networks on microcontrollers
Internet of Things (IoT) systems provide large amounts of data on all aspects of human
behavior. Machine learning techniques, especially deep neural networks (DNN), have …
behavior. Machine learning techniques, especially deep neural networks (DNN), have …
Towards data-efficient continuous learning for edge video analytics via smart caching
Continuous learning (CL) has recently been adopted into edge video analytics, gaining
huge success in maintaining high accuracy without constantly retraining DNN models by …
huge success in maintaining high accuracy without constantly retraining DNN models by …
Latent generative replay for resource-efficient continual learning of facial expressions
S Stoychev, N Churamani… - 2023 IEEE 17th …, 2023 - ieeexplore.ieee.org
Real-world Facial Expression Recognition (FER) systems require models to constantly learn
and adapt with novel data. Traditional Machine Learning (ML) approaches struggle to adapt …
and adapt with novel data. Traditional Machine Learning (ML) approaches struggle to adapt …
DOCTOR: A multi-disease detection continual learning framework based on wearable medical sensors
Modern advances in machine learning (ML) and wearable medical sensors (WMSs) in edge
devices have enabled ML-driven disease detection for smart healthcare. Conventional ML …
devices have enabled ML-driven disease detection for smart healthcare. Conventional ML …