Exploring system performance of continual learning for mobile and embedded sensing applications
Continual learning approaches help deep neural network models adapt and learn
incrementally by trying to solve catastrophic forgetting. However, whether these existing …
incrementally by trying to solve catastrophic forgetting. However, whether these existing …
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 …
LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms
Continual Learning (CL) allows applications such as user personalization and household
robots to learn on the fly and adapt to context. This is an important feature when context …
robots to learn on the fly and adapt to context. This is an important feature when context …
Enabling on-device smartphone GPU based training: Lessons learned
Deep Learning (DL) has shown impressive performance in many mobile applications. Most
existing works have focused on reducing the computational and resource overheads of …
existing works have focused on reducing the computational and resource overheads of …
FastICARL: Fast incremental classifier and representation learning with efficient budget allocation in audio sensing applications
Various incremental learning (IL) approaches have been proposed to help deep learning
models learn new tasks/classes continuously without forgetting what was learned previously …
models learn new tasks/classes continuously without forgetting what was learned previously …
IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning
Like generic multi-task learning, continual learning has the nature of multi-objective
optimization, and therefore faces a trade-off between the performance of different tasks. That …
optimization, and therefore faces a trade-off between the performance of different tasks. That …
Myokey: Inertial motion sensing and gesture-based qwerty keyboard for extended realities
Usability challenges and social acceptance of textual input in a context of extended realities
(XR) motivate the research of novel input modalities. We investigate the fusion of inertial …
(XR) motivate the research of novel input modalities. We investigate the fusion of inertial …
[PDF][PDF] Third Year Report
YD Kwon - 2023 - theyoungkwon.github.io
2. Background. This chapter describes the relevant research in more details in the areas of
on-device ML and CL to discuss the necessity, novelty, and contributions of this thesis. 3 …
on-device ML and CL to discuss the necessity, novelty, and contributions of this thesis. 3 …
[PDF][PDF] Efficient Meta Continual Learning on the Edge
YD Kwon - theyoungkwon.github.io
Continual Learning (CL) methods are designed to help deep neural networks to adapt and
learn new tasks/knowledge without forgetting previously learned tasks. In recent years …
learn new tasks/knowledge without forgetting previously learned tasks. In recent years …