no code implementations • 28 Dec 2023 • Hankyul Baek, Donghyeon Kim, Joongheon Kim
Spurred by consistent advances and innovation in deep learning, object detection applications have become prevalent, particularly in autonomous driving that leverages various visual data.
no code implementations • 4 Dec 2022 • Won Joon Yun, Jae Pyoung Kim, Hankyul Baek, Soyi Jung, Jihong Park, Mehdi Bennis, Joongheon Kim
While witnessing the noisy intermediate-scale quantum (NISQ) era and beyond, quantum federated learning (QFL) has recently become an emerging field of study.
no code implementations • 12 Nov 2022 • Won Joon Yun, Hankyul Baek, Joongheon Kim
In recent years, the field of quantum science has attracted significant interest across various disciplines, including quantum machine learning, quantum communication, and quantum computing.
no code implementations • 7 Nov 2022 • Hankyul Baek, Yoo Jeong, Ha, MinJae Yoo, Soyi Jung, Joongheon Kim
In modern on-driving computing environments, many sensors are used for context-aware applications.
no code implementations • 30 Oct 2022 • Won Joon Yun, Hankyul Baek, Joongheon Kim
In recent years, quantum machine learning (QML) has been actively used for various tasks, e. g., classification, reinforcement learning, and adversarial learning.
no code implementations • 18 Oct 2022 • Hankyul Baek, Won Joon Yun, Joongheon Kim
Moreover, a quantum convolutional neural network (QCNN) is the quantum-version of CNN because it can process high-dimensional vector inputs in contrast to QNN.
no code implementations • 26 Sep 2022 • Hankyul Baek, Won Joon Yun, Joongheon Kim
With the beginning of the noisy intermediate-scale quantum (NISQ) era, quantum neural network (QNN) has recently emerged as a solution for the problems that classical neural networks cannot solve.
no code implementations • 26 Mar 2022 • Won Joon Yun, Yunseok Kwak, Hankyul Baek, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim
However, applying FL in practice is challenging due to the local devices' heterogeneous energy, wireless channel conditions, and non-independently and identically distributed (non-IID) data distributions.
no code implementations • 5 Dec 2021 • Hankyul Baek, Won Joon Yun, Yunseok Kwak, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim
By applying SC, SlimFL exchanges the superposition of multiple width configurations that are decoded as many as possible for a given communication throughput.
no code implementations • 5 Dec 2021 • Hankyul Baek, Won Joon Yun, Soyi Jung, Jihong Park, Mingyue Ji, Joongheon Kim, Mehdi Bennis
To address the heterogeneous communication throughput problem, each full-width (1. 0x) SNN model and its half-width ($0. 5$x) model are superposition-coded before transmission, and successively decoded after reception as the 0. 5x or $1. 0$x model depending on the channel quality.