检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Jung, Sangwon Chun, Sanghyuk Moon, Taesup Department of ECE/ASRI Seoul National University Korea Republic of NAVER AI Lab Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Recently, fairness-aware learning have become increasingly crucial, but most of those methods operate by assuming the availability of fully annotated demographic group labels. We emphasize that such assumption is unrealistic for real-world applications since group label annotations are expensive and can conflict with privacy issues. In this paper, we consider a more practical scenario, dubbed as Algorithmic Group Fairness with the Partially annotated Group labels (Fair-PG). We observe that the existing methods to achieve group fairness perform even worse than the vanilla training, which simply uses full data only with target labels, under Fair-PG. To address this problem, we propose a simple Confidence-based Group Label assignment (CGL) strategy that is readily applicable to any fairness-aware learning method. CGL utilizes an auxiliary group classifier to assign pseudo group labels, where random labels are assigned to low confident samples. We first theoretically show that our method design is better than the vanilla pseudo-labeling strategy in terms of fairness criteria. Then, we empirically show on several benchmark datasets that by combining CGL and the state-of-the-art fairness-aware in-processing methods, the target accuracies and the fairness metrics can be jointly improved compared to the baselines. Furthermore, we convincingly show that CGL enables to naturally augment the given group-labeled dataset with external target label-only datasets so that both accuracy and fairness can be improved. Code is available at https://***/naver-ai/cgl_fairness. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards High Generalization Performance on Electrocardiogram Classification

Towards High Generalization Performance on Electrocardiogram...

引用

2021 Computing in Cardiology, CinC 2021

作者： Han, Hyeongrok Park, Seongjae Min, Seonwoo Choi, Hyun-Soo Kim, Eunji Kim, Hyunki Park, Sangha Kim, Jinkook Park, Junsang An, Junho Lee, Kwanglo Jeong, Wonsun Chon, Sangil Ha, Kwonwoo Han, Myungkyu Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of HUINNO Co. Ltd Seoul Korea Republic of LG AI Research Seoul Korea Republic of Department of Computer Science and Engineering Kangwon National University Chuncheon Korea Republic of Department of Biological Sciences Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence ASRI INMC Institute of Engineering Research Seoul National University Seoul Korea Republic of

ISBN: (纸本)9781665479165

Recently, many electrocardiogram (ECG) classification algorithms using deep learning have been proposed. The characteristics of ECG vary from dataset to dataset for various reasons (i.e., hospital, race, etc.). Therefore, it is important for a model to have high generalization performance consistently over all datasets. In this paper, as part of the PhysioNet / Computing in Cardiology Challenge 2021, we present a model developed to classify cardiac abnormalities from 12 lead and reduced-lead ECGs. In particular, to upgrade our previous model for improving generalization performance, we newly adopt constant-weighted cross-entropy loss, additional features, Mixup augmentation, and squeeze/excitation block, OneCycle learning rate scheduler, which are selected via evaluation of generalization performance using leave-one-dataset-out cross-validation setting. With the present model, our DSAILSNU team has received challenge scores of 0.55, 0.58, 0.58, 0.57 and 0.57 (ranked 2nd, 1st, 1st, 2nd, 2nd out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set, respectively. The present model achieves higher generalization performance over all versions of the hidden test set than the model submitted last year. © 2021 Creative Commons.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Pre-Training of Deep Bidirectional Protein Sequence Representations With Structural Information

引用

IEEE ACCESS 2021年 9卷 123912-123926页

作者： Min, Seonwoo Park, Seunghyun Kim, Siwon Choi, Hyun-Soo Lee, Byunghan Yoon, Sungroh Seoul Natl Univ Dept Elect & Comp Engn Seoul 08826 South Korea LG AI Res Seoul 07796 South Korea NAVER Corp Clova AI Res Seongnam 13561 South Korea Kangwon Natl Univ Dept Comp Sci & Engn Chunchon 24341 South Korea Seoul Natl Univ Sci & Technol Dept Elect & IT Media Engn Seoul 01811 South Korea Seoul Natl Univ INMC ASRI Interdisciplinary Program Artificial Intelligence Seoul 08826 South Korea Seoul Natl Univ Inst Engn Res Seoul 08826 South Korea

Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role. All the data and codes used in this study are available at https://***/mswzeus/PLUS.

关键词： Task analysis Biological system modeling Protein sequence Biology Computational modeling Training Predictive models Protein sequence protein structure representation learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS

arXiv

引用

arXiv 2021年

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of AIIS ASRI INMC ISRC NSI Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Towards High Generalization Performance on Electrocardiogram Classification

Towards High Generalization Performance on Electrocardiogram...

引用

Computers in Cardiology (CinC)

作者： Hyeongrok Han Seongjae Park Seonwoo Min Hyun-Soo Choi Eunji Kim Hyunki Kim Sangha Park Jinkook Kim Junsang Park Junho An Kwanglo Lee Wonsun Jeong Sangil Chon Kwonwoo Ha Myungkyu Han Sungroh Yoon Seoul National University Seoul South Korea HUINNO Co. Ltd. Seoul South Korea LG AI Research Seoul South Korea Kangwon National University Chuncheon South Korea Interdisciplinary Program in Bioinformatics Interdisciplinary Program in Artificial Intelligence ASRI INMC and Institute of Engineering Research Seoul National University Seoul South Korea

ISBN: (纸本)9781665467216

Recently, many electrocardiogram (ECG) classification algorithms using deep learning have been proposed. The characteristics of ECG vary from dataset to dataset for various reasons (i.e., hospital, race, etc.). Therefore, it is important for a model to have high generalization performance consistently over all datasets. In this paper, as part of the PhysioNet / Computing in Cardiology Challenge 2021, we present a model developed to classify cardiac abnormalities from 12 lead and reduced-lead ECGs. In particular, to upgrade our previous model for improving generalization performance, we newly adopt constant-weighted cross-entropy loss, additional features, Mixup augmentation, and squeeze/excitation block, OneCycle learning rate scheduler, which are selected via evaluation of generalization performance using leave-one-dataset-out cross-validation setting. With the present model, our DSAIL_SNU team has received challenge scores of 0.55, 0.58, 0.58, 0.57 and 0.57 (ranked 2nd, 1st, 1st, 2nd, 2nd out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set, respectively. The present model achieves higher generalization performance over all versions of the hidden test set than the model submitted last year.

关键词： Deep learning Hospitals Computational modeling Electrocardiography Lead Classification algorithms Cardiology

来源：评论

学校读者我要写书评

暂无评论

Training energy-efficient deep spiking neural networks with time-to-first-spike coding

arXiv

引用

arXiv 2021年

作者： Park, Seongsik Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Institute of New Media and Communications Seoul National University Seoul08826 Korea Republic of ASRI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The tremendous energy consumption of deep neural networks (DNNs) has become a serious problem in deep learning. Spiking neural networks (SNNs), which mimic the operations in the human brain, have been studied as prominent energy-efficient neural networks. Due to their event-driven and spatiotemporally sparse operations, SNNs show possibilities for energy-efficient processing. To unlock their potential, deep SNNs have adopted temporal coding such as time-to-first-spike (TTFS) coding, which represents the information between neurons by the first spike time. With TTFS coding, each neuron generates one spike at most, which leads to a significant improvement in energy efficiency. Several studies have successfully introduced TTFS coding in deep SNNs, but they showed restricted efficiency improvement owing to the lack of consideration for efficiency during training. To address the aforementioned issue, this paper presents training methods for energy-efficient deep SNNs with TTFS coding. We introduce a surrogate DNN model to train the deep SNN in a feasible time and analyze the effect of the temporal kernel on training performance and efficiency. Based on the investigation, we propose stochastically relaxed activation and initial value-based regularization for the temporal kernel parameters. In addition, to reduce the number of spikes even further, we present temporal kernel-aware batch normalization. With the proposed methods, we could achieve comparable training results with significantly reduced spikes, which could lead to energy-efficient deep SNNs. © 2021, CC BY.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Noise-robust deep spiking neural networks with temporal information

arXiv

引用

arXiv 2021年

作者： Park, Seongsik Lee, Dongjin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Institute of New Media and Communications Seoul National University Seoul08826 Korea Republic of Asri and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information. SNNs have shown a superior efficiency on neuromorphic devices, but the devices are susceptible to noise, which hinders them from being applied in real-world applications. Several studies have increased noise robustness, but most of them considered neither deep SNNs nor temporal information. In this paper, we investigate the effect of noise on deep SNNs with various neural coding methods and present a noise-robust deep SNN with temporal information. With the proposed methods, we have achieved a deep SNN that is efficient and robust to spike deletion and jitter. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Noise-Robust Deep Spiking Neural Networks with Temporal Information 21

Noise-Robust Deep Spiking Neural Networks with Temporal Info...

引用

Proceedings of the 58th Annual ACM/IEEE Design Automation Conference

作者： Seongsik Park Dongjin Lee Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Seoul South Korea and Institute of New Media and Communications Seoul National University Seoul South Korea Department of Electrical and Computer Engineering Seoul National University Seoul South Korea Department of Electrical and Computer Engineering Seoul National University Seoul South Korea and Institute of New Media and Communications Seoul National University Seoul South Korea and ASRI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul South Korea

ISBN: (纸本)9781665432740

关键词： neural coding

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Stego: Training-free diffusion generative steganography via message projection

引用

Information Sciences 2025年 718卷

作者： Daegyu Kim Chaehun Shin Jooyoung Choi Dahuin Jung Sungroh Yoon Data Science and AI Laboratory Electrical and Computer Engineering Seoul National University Seoul 08826 Republic of Korea School of Computer Science and Engineering Soongsil University Seoul 06978 Republic of Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul 08826 Republic of Korea AIIS ASRI INMC and ISRC Seoul National University Seoul 08826 Republic of Korea

Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection ability over cover images. However, they create relatively unrealistic stego images because of the inherent limitations of generative models. We propose Diffusion-Stego, a generative steganography approach based on diffusion models that outperform other generative models in image generation. Diffusion-Stego projects secret messages into the latent noise of diffusion models and generates stego images with an iterative denoising process. Since the naive hiding of secret messages into noise boosts visual degradation and decreases extracted message accuracy, we introduce message projection, which hides messages into noise space while addressing these issues. We suggest three options for message projection to adjust the trade-off between extracted message accuracy, anti-detection ability, and image quality. Diffusion-Stego is a training-free approach, so we can apply it to pre-trained diffusion models that generate high-quality images, or even large-scale text-to-image models, such as Stable diffusion. Diffusion-Stego achieved a high capacity of messages as well as high quality that makes it challenging to distinguish from real images in the PNG format.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bag of Tricks for Electrocardiogram Classification With Deep Neural Networks

Bag of Tricks for Electrocardiogram Classification With Deep...

引用

Computing in Cardiology Conference (CinC)

作者： Min, Seonwoo Choi, Hyun-Soo Han, Hyeongrok Seo, Minji Kim, Jin-Kook Park, Junsang Jung, Sunghoon Oh, Il-Young Lee, Byunghan Yoon, Sungroh Seoul Natl Univ Dept Elect & Comp Engn Seoul South Korea SK Telecom T3K Seoul South Korea HUINNO Co Ltd Seoul South Korea Seoul Natl Univ Div Cardiol Dept Internal Med Bundang Hosp Seongnam South Korea Seoul Natl Univ Sci & Technol Dept Elect & IT Media Engn Seoul South Korea Seoul Natl Univ Dept Biol Sci Interdisciplinary Program BioinformatASRIINMC Interdisciplinary Program Artificial Intelligence Seoul South Korea Seoul Natl Univ Inst Engn Res Seoul South Korea

ISBN: (纸本)9781728173825

Recent algorithmic advances in electrocardiogram (ECG) classification are largely contributed to deep learning. However, these methods are still based on a relatively straightforward application of deep neural networks (DNNs), which leaves incredible room for improvement. In this paper, as part of the PhysioNet / Computing in Cardiology Challenge 2020, we developed an 18-layer residual convolutional neural network to classify clinical cardiac abnormalities from 12-lead ECG recordings. We focused on examining a collection of data pre-processing, model architecture, training, and post-training procedure refinements for DNN-based ECG classification. We showed that by combining these refinements, we can improve the classification performance significantly. Our team, DSAIL SNU, obtained a 0.695 challenge score using 10-fold cross-validation, and a 0.420 challenge score on the full test data, placing us 6th in the official ranking.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：