Search Results for author: Xinyue Wang

Found 12 papers, 4 papers with code

X-MLP: A Patch Embedding-Free MLP Architecture for Vision

no code implementations2 Jul 2023 Xinyue Wang, Zhicheng Cai, Chenglei Peng

However, existing vision MLP architectures always depend on convolution for patch embedding.

Iterative-in-Iterative Super-Resolution Biomedical Imaging Using One Real Image

no code implementations26 Jun 2023 Yuanzheng Ma, Xinyue Wang, Benqi Zhao, Ying Xiao, Shijie Deng, Jian Song, Xun Guan

Deep learning-based super-resolution models have the potential to revolutionize biomedical imaging and diagnoses by effectively tackling various challenges associated with early detection, personalized medicine, and clinical automation.


Recognizable Information Bottleneck

1 code implementation28 Apr 2023 Yilin Lyu, Xin Liu, Mingyang Song, Xinyue Wang, Yaxin Peng, Tieyong Zeng, Liping Jing

The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound.

Look-Ahead AC Optimal Power Flow: A Model-Informed Reinforcement Learning Approach

no code implementations4 Mar 2023 Xinyue Wang, Haiwang Zhong, Guanglun Zhang, Guangchun Ruan, Yiliu He, Zekuan Yu

With the increasing proportion of renewable energy in the generation side, it becomes more difficult to accurately predict the power generation and adapt to the large deviations between the optimal dispatch scheme and the day-ahead scheduling in the process of real-time dispatch.

Decision Making reinforcement-learning +2

Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

no code implementations21 Sep 2022 Zekuan Yu, Guangchun Ruan, Xinyue Wang, Guanglun Zhang, Yiliu He, Haiwang Zhong

In this paper, we propose an evaluation approach to analyze the performance of RL agents in a look-ahead economic dispatch scheme.

reinforcement-learning Reinforcement Learning (RL)

Learning Causal Discovery

1 code implementation12 Sep 2022 Xinyue Wang, Konrad Paul Kording

Causal discovery (CD) from time-varying data is important in neuroscience, medicine, and machine learning.

Causal Discovery Meta-Learning

Neural Networks as Paths through the Space of Representations

no code implementations22 Jun 2022 Richard D. Lange, Devin Kwok, Jordan Matelsky, Xinyue Wang, David S. Rolnick, Konrad P. Kording

Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand.

Interpretable Image Recognition by Constructing Transparent Embedding Space

2 code implementations ICCV 2021 Jiaqi Wang, Huafeng Liu, Xinyue Wang, Liping Jing

This plug-in embedding space is spanned by transparent basis concepts which are constructed on the Grassmann manifold.

Deep Generative Model for Robust Imbalance Classification

no code implementations CVPR 2020 Xinyue Wang, Yilin Lyu, Liping Jing

In this paper, a deep generative classifier is proposed to mitigate this issue via both data perturbation and model perturbation.

Classification General Classification

Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin

no code implementations21 Nov 2019 Bryan Li, Xinyue Wang, Homayoon Beigi

We propose a system to develop a basic automatic speech recognizer(ASR) for Cantonese, a low-resource language, through transfer learning of Mandarin, a high-resource language.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Cannot find the paper you are looking for? You can Submit a new open access paper.