no code implementations • 10 Mar 2024 • Chunhui Gu, Ruosha Li, Guoqiang Zhang
Conclusions: The reporting quality of the PSM analysis is suboptimal in some COVID-19 epidemiological studies.
no code implementations • 21 Nov 2023 • Sipei Zhao, Guoqiang Zhang, Eva Cheng, Ian S. Burnett
A Personal Sound Zones (PSZ) system aims to generate two or more independent listening zones that allow multiple users to listen to different music/audio content in a shared space without the need for wearing headphones.
1 code implementation • 10 Jul 2023 • Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn
In our work, it is found that applying BDIA to the EDM sampling procedure produces consistently better performance over four pre-trained models.
1 code implementation • CVPR 2023 • Guoqiang Zhang, Niwa Kenta, W. Bastiaan Kleijn
We propose lookahead diffusion probabilistic models (LA-DPMs) to exploit the correlation in the outputs of the deep neural networks (DNNs) over subsequent timesteps in diffusion probabilistic models (DPMs) to refine the mean estimation of the conditional Gaussian distributions in the backward process.
no code implementations • 22 Apr 2023 • Guoqiang Zhang, Niwa Kenta, W. Bastiaan Kleijn
A popular approach to sample a diffusion-based generative model is to solve an ordinary differential equation (ODE).
no code implementations • 2 Feb 2023 • Guoqiang Zhang
A number of recent adaptive optimizers improve the generalisation performance of Adam by essentially reducing the variance of adaptive stepsizes to get closer to SGD with momentum.
1 code implementation • 24 Mar 2022 • Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn
Firstly, we show that the particular placement of the parameter epsilon within the update expressions of AdaBelief reduces the range of the adaptive stepsizes, making AdaBelief closer to SGD with momentum.
no code implementations • 9 Dec 2021 • Guoqiang Zhang, Niwa Kenta, W. Bastiaan Kleijn
Aida is designed to compute the qth power of the magnitude in the form of |m_{t+1}|^q/(r_{t+1}+epsilon)^(q/p) (or |m_{t+1}|^q/((r_{t+1})^(q/p)+epsilon)), which reduces to that of AdamW when (p, q)=(2, 1).
no code implementations • 5 Oct 2021 • Xipeng Shen, Guoqiang Zhang, Irene Dea, Samantha Andow, Emilio Arroyo-Fang, Neal Gafter, Johann George, Melissa Grueter, Erik Meijer, Steffi Stumpos, Alanna Tempest, Christy Warden, Shannon Yang
This paper presents a novel optimization for differentiable programming named coarsening optimization.
no code implementations • 26 Sep 2021 • Yubo An, Shenghui Zhao, Guoqiang Zhang
This paper investigates the underlying complementarity between the frame-level and shot-level methods, and a stacking ensemble approach is proposed for supervised video summarization.
1 code implementation • 20 Feb 2021 • Haimin Zhang, Min Xu, Guoqiang Zhang, Kenta Niwa
We show that applying stochastic scaling at the gradient level is complementary to that applied at the feature level to improve the overall performance.
no code implementations • 31 Dec 2020 • Guoqiang Zhang, Liming Ling, Zhenya Yan
We first report the first- and higher-order vector Peregrine solitons (alias rational rogue waves) for the any multi-component NLS equations based on the loop group theory, an explicit (n + 1)-multiple eigenvalue of a characteristic polynomial of degree (n + 1) related to the condition of Benjamin-Feir instability, and inverse functions.
Exactly Solvable and Integrable Systems Mathematical Physics Analysis of PDEs Mathematical Physics Pattern Formation and Solitons Computational Physics
no code implementations • 31 Dec 2020 • Guoqiang Zhang, Liming Ling, Zhenya Yan, Vladimir V. Konotop
The extreme events are investigated for an $n$-component nonlinear Schr\"odinger ($n$-NLS) system in the focusing Kerr-like nonlinear media, which appears in many physical fields.
Exactly Solvable and Integrable Systems Mathematical Physics Analysis of PDEs Mathematical Physics Pattern Formation and Solitons Optics
1 code implementation • COLING 2020 • Xu Zhang, Yifeng Li, Wenpeng Lu, Ping Jian, Guoqiang Zhang
Sentence intention matching is vital for natural language understanding.
no code implementations • 17 Nov 2020 • Jiyang Xie, Zhanyu Ma, Jing-Hao Xue, Guoqiang Zhang, Jun Guo
In the DS-UI, we combine the classifier of a DNN, i. e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer.
1 code implementation • 11 Oct 2020 • Jiyang Xie, Zhanyu Ma, and Jianjun Lei, Guoqiang Zhang, Jing-Hao Xue, Zheng-Hua Tan, Jun Guo
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs).
no code implementations • 27 Sep 2018 • Guoqiang Zhang, Kenta Niwa, W. Bastiaan Kleijn
Empirical studies for training four convolutional neural networks over MNIST and CIFAR10 show that under proper parameter selection, Game produces promising validation performance as compared to AMSGrad and PAdam.