检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

23 篇 会议

馆藏范围

23 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

17 篇 工学
- 13 篇 计算机科学与技术...
- 12 篇 软件工程
- 5 篇 生物工程
- 3 篇 土木工程
- 2 篇 信息与通信工程
- 1 篇 力学（可授工学、理...
- 1 篇 机械工程
- 1 篇 材料科学与工程（可...
- 1 篇 动力工程及工程热...
- 1 篇 电气工程
- 1 篇 电子科学与技术（可...
- 1 篇 建筑学
- 1 篇 化学工程与技术
13 篇 理学
- 10 篇 数学
- 8 篇 统计学（可授理学、...
- 5 篇 生物学
- 1 篇 化学
1 篇 教育学
- 1 篇 教育学
- 1 篇 心理学(可授教育学...
1 篇 文学
- 1 篇 中国语言文学
- 1 篇 外国语言文学
1 篇 管理学
- 1 篇 图书情报与档案管...

主题

9 篇 generative adver...
2 篇 deep neural netw...
1 篇 tools
1 篇 free energy
1 篇 reinforcement le...
1 篇 libraries
1 篇 statistical anal...
1 篇 gallium nitride
1 篇 discriminators
1 篇 time series
1 篇 graphical user i...
1 篇 proteins
1 篇 maximum likeliho...
1 篇 dynamics
1 篇 heuristic method...
1 篇 training

机构

4 篇 google brain uni...
2 篇 deepmind united ...
1 篇 max-planck insti...
1 篇 virginia tech. u...
1 篇 department of bi...
1 篇 mila université ...
1 篇 university of ca...
1 篇 department of st...
1 篇 simulamet
1 篇 csail mit united...
1 篇 columbia univers...
1 篇 toyota technolog...
1 篇 university of ca...
1 篇 wuhan university
1 篇 eth zurich depar...
1 篇 machine learning...
1 篇 stanford univers...
1 篇 department of ap...
1 篇 vehicle technolo...
1 篇 university of to...

作者

2 篇 tucker george
2 篇 anonymous
2 篇 dinh laurent
1 篇 schölkopf bernha...
1 篇 fan shuangfei
1 篇 ingraham john
1 篇 zhang zijun
1 篇 prabhu vinay uda...
1 篇 bernstein michae...
1 篇 narcomey austin
1 篇 poole ben
1 篇 haile mulugeta a...
1 篇 darrell trevor
1 篇 krishna ranjay
1 篇 garg vikas k.
1 篇 cunningham john ...
1 篇 larochelle hugo
1 篇 m. zaheer
1 篇 vinyals oriol
1 篇 durr nicholas j.

语言

23 篇 英文

检索条件"任意字段=2019 Deep Generative Models for Highly Structured Data, DGS@ICLR 2019 Workshop"

共 23 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

deep generative models for highly structured data, dgs@iclr 2019 workshop

Deep Generative Models for Highly Structured Data, DGS@ICLR ...

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

The proceedings contain 42 papers. The topics discussed include: generating molecules via chemical reactions;a seed-augment-train framework for universal digit classification;learning deep latent-variable MRFS with amortized Bethe free energy minimization;unsupervised demixing of structured signals from their superposition using GANs;learning to defense by learning to attack;smoothing nonlinear variational objectives with sequential Monte Carlo;adjustable real-time style transfer;on the relationship between normalizing flows and variational- and denoising autoencoders;disentangled state space models: unsupervised learning of dynamics across heterogeneous environments;compositional GAN: learning image-conditional binary composition;AlignFlow: learning from multiple domains via normalizing flows;and dual space learning with variational autoencoders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Debiasing deep generative models via likelihood-free importance weighting

Debiasing deep generative models via likelihood-free importa...

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Anonymous

A learned generative model often gives biased statistics relative to the underlying data distribution. A standard technique to correct this bias is by importance weighting samples from the model by the likelihood ratio under the model and true distributions. When the likelihood ratio is unknown, it can be estimated by training a probabilistic classifier to distinguish samples from the two distributions. In this paper, we employ this likelihood-free importance weighting framework to correct for the bias in using state-of-the-art deep generative models. We find that this technique consistently improves standard goodness-of-fit metrics for evaluating the sample quality of state-of-the-art generative models, suggesting reduced bias. Finally, we demonstrate its utility on representative applications in a) data augmentation for classification using generative adversarial networks, and b) model-based policy evaluation using off-policy data. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

deep generative models for generating labeled graphs

Deep generative models for generating labeled graphs

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Fan, Shuangfei Huang, Bert Virginia Tech. United States

As a new way to train generative models, generative adversarial networks (GANs) have achieved considerable success in image generation, and this framework has also recently been applied to data with graph structures. We identify the drawbacks of existing deep frameworks for generating graphs, and we propose labeledgraph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels. We test the approach with different discriminative models as well as different GAN frameworks on various types of graph datasets, such as collections of citation networks and protein graphs. Experiment results show that our model can generate diverse labeled graphs that match the structural characteristics of the training data and outperforms all baselines in terms of quality, generality, and scalability. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised demixing of structured signals from their superposition using GANs

Unsupervised demixing of structured signals from their super...

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Anonymous

Recently, generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are easily available. However, in many applications, this assumption is violated. In this paper, we consider the observation setting in which the samples from a target distribution are given by the superposition of two structured components, and leverage GANs for learning of the structure of the components. We propose a novel framework, demixing-GAN, which learns the distribution of two components at the same time. Through extensive numerical experiments, we demonstrate that the proposed framework can generate clean samples from unknown distributions, which further can be used in demixing of the unseen test images. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Perceptual generative autoencoders

Perceptual generative autoencoders

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Zhang, Zijun Zhang, Ruixiang Li, Zongpeng Bengio, Yoshua Paull, Liam University of Calgary Canada MILA Université de Montréal Canada Wuhan University China

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimensionality of data can be much lower than the ambient dimensionality. We argue that this discrepancy may contribute to the difficulties in training generative models. We therefore propose to map both the generated and target distributions to the latent space using the encoder of a standard autoencoder, and train the generator (or decoder) to match the target distribution in the latent space. The resulting method, perceptual generative autoencoder (PGA), is then incorporated with maximum likelihood or variational autoencoder (VAE) objective to train the generative model. With maximum likelihood, PGA generalizes the idea of reversible generative models to unrestricted neural network architectures and arbitrary latent dimensionalities. When combined with VAE, PGA can generate sharper samples than vanilla VAE. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

generative models for graph-based protein design

Generative models for graph-based protein design

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Ingraham, John Garg, Vikas K. Barzilay, Regina Jaakkola, Tommi CSAIL MIT United States

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice. A significant aspect of this challenge is the complex coupling between protein sequence and 3D structure, and the task of finding a viable design is often referred to as the inverse protein folding problem. We develop generative models for protein sequences conditioned on a graph-structured specification of the design target. Our approach efficiently captures the complex dependencies in proteins by focusing on those that are long-range in sequence but local in 3D space. Our framework significantly improves upon prior parametric models of protein sequences given structure, and takes a step toward rapid and targeted biomolecular design with the aid of deep generative models. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Compositional gan (Extended abstract): Learning image-conditional binary composition

Compositional gan (Extended abstract): Learning image-condit...

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Azadi, Samaneh Pathak, deepak Ebrahimi, Sayna Darrell, Trevor University of California Berkeley United States

generative Adversarial Networks (GANs) can produce images of surprising complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different objects in the world, including their relative scaling, spatial layout, occlusion, or viewpoint transformation is a challenging problem. In this work, we compose a pair of objects in a conditional GAN framework using a novel self-consistent composition-by-decomposition network. Given object images from two distinct distributions, our model can generate a realistic composite image from their joint distribution following the texture and shape of the input objects. Our results reveal that the learned model captures potential interactions between the two object domains, and can output their realistic composed scenes at test time. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A rad approach to deep mixture models

A rad approach to deep mixture models

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Dinh, Laurent Sohl-Dickstein, Jascha Pascanu, Razvan Larochelle, Hugo Google Brain United States DeepMind United Kingdom

Flow based models such as REAL NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities over a continuous input space into similarly continuous distributions over continuous latent variables. This makes them poorly suited for modeling and representing discrete structures in data distributions, for example class membership or discrete symmetries. To address this difficulty, we present a normalizing flow architecture which relies on domain partitioning using locally invertible functions, and possesses both real and discrete valued latent variables. This Real and Discrete (RAD) approach retains the desirable normalizing flow properties of exact sampling, exact inference, and analytically computable probabilities, while at the same time allowing simultaneous modeling of both continuous and discrete structure in a data distribution. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

structured prediction using cGANs with fusion discriminator

Structured prediction using cGANs with fusion discriminator

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Mahmood, Faisal Xu, Wenhao Durr, Nicholas J. Johnson, Jeremiah W. Yuille, Alan Department of Biomedical Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Applied Engineering and Sciences University of New Hampshire ManchesterNH03101 United States Department of Computer Science Johns Hopkins University BaltimoreMD21218 United States

We propose the fusion discriminator, a single unified framework for incorporating conditional information into a generative adversarial network (GAN) for a variety of distinct structured prediction tasks, including image synthesis, semantic segmentation, and depth estimation. Much like commonly used convolutional neural network - conditional Markov random field (CNN-CRF) models, the proposed method is able to enforce higher-order consistency in the model, but without being limited to a very specific class of potentials. The method is conceptually simple and flexible, and our experimental results demonstrate improvement on several diverse structured prediction tasks. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

Disentangled state space models: Unsupervised learning of dynamics across heterogeneous environments

Disentangled state space models: Unsupervised learning of dy...

引用

2019 deep generative models for highly structured data, dgs@iclr 2019 workshop

作者： Miladinović, Dorde Buhmann, Joachim M. Gondal, Waleed Schölkopf, Bernhard Bauer, Stefan ETH Zurich Department for Computer Science Switzerland Max-Planck Institute for Intelligent Systems Germany

Sequential data often originates from diverse environments. Across them exist both shared regularities and environment specifics. To learn robust cross-environment descriptions of sequences we introduce disentangled state space models (DSSM). In the latent space of DSSM environment-invariant state dynamics is explicitly disentangled from environment-specific information governing that dynamics. We empirically show that such separation enables robust prediction, sequence manipulation and environment characterization. We also propose an unsupervised VAE-based training procedure to learn DSSM as Bayesian filters. In our experiments, we demonstrate state-of-the-art performance in controlled generation and prediction of bouncing ball video sequences across varying gravitational influences. © deep generative models for highly structured data, dgs@iclr 2019 *** right reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共3页 << < 1 2 3 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：