乐胖代购免代理版

Bitcoin: A Peer-to-Peer Electronic Cash System（比特币论文翻译）

比特币历史： 2008年，比特币论文诞生 2009年1月，第一批比

时间戳

接受者

原创 2023-08-02 19:32:24 175 阅读

GAN（Generative Adversarial Nets）的发展

GAN（Generative Adversarial Nets），产生式对抗网络存在问题： 1.无法表示数据分布 2.速度慢 3.resolution太小，大了无语义信息 4.无r

语义信息

生成器

sed

原创 2022-08-10 17:26:23 294 阅读

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Defferrard, Michaël, Xavier Bresson, and Pierre Vandergheynst. "Convolutional neural networks on graphs with fast localized spectral filtering." Advan

卷积

复杂度

github

原创 2022-08-10 17:24:47 295 阅读

Geometric deep learning on graphs and manifolds using mixture model CNNs

Monti, Federico, et al. "Geometric deep learning on graphs and manifolds using mixture model CNNs." arXiv preprint arXiv:1611.08402 (2016). 作者

数据

深度学习

图结构

原创 2022-08-10 17:24:46 197 阅读

Semi-Supervised Classification with Graph Convolutional Networks

Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). 作者对Convo

sed

github

原创 2022-07-16 00:15:37 134 阅读

GRAPH ATTENTION NETWORKS

基本就是第一层concatenate，第二层不concatenate. 相关论文： Semi-Supervised Classification with Graph Convolutional Networks Geometric deep learning on graphs and manif

sed

github

原创 2022-07-16 00:15:27 128 阅读

Generalization and Equilibrium in Generative Adversarial Nets

Paper link: https://arxiv.org/abs/1703.00573 Blog link: http://www.offconvex.org/2017/03/30/GANs2/ Github: https://github.com/PrincetonML/MIX-plus-GAN

github

拟合

损失函数

原创 2022-07-15 22:07:50 80 阅读

Learning to act by predicting the future

Dosovitskiy, Alexey, and Vladlen Koltun. "Learning to act by predicting the future." arXiv preprint arXiv:1611.01779 (2016). vizdoom比赛track2的冠军。要点： 1

泛化

d3

sed

原创 2022-07-15 22:06:20 56 阅读

DSSM(DEEP STRUCTURED SEMANTIC MODELS)

Huang, Po-Sen, et al. "Learning deep structured semantic models for web search using clickthrough data." Proceedings of the 22nd ACM international con

有监督学习

相似度

github

原创 2022-07-15 22:06:07 91 阅读

The Properties of Posterior of Topic Model

1.Tang, Jian, et al. "Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis." ICML. 2014. This is the best paper of

数据

github

数据集

原创 2022-07-15 21:25:06 19 阅读

Papers of Word Embeddings

首先解释一下什么叫做embedding。举个例子：地图就是对于现实地理的embedding，现实的地理地形的信息其实远远超过三维但是地图通过颜色和等高线等来最大化表现现实的地理信息。 embedding就是用固定的维度来最大化表现原始信息。embedding可以翻译为向量或者表示。 1.Hashimoto, Tatsunori B., David Alvarez-Melis, and

地理信息

github

原创 2022-07-15 21:24:49 63 阅读

Style Lessons in Clarity and Grace (11th Edition)中文翻译

Joseph, Williams. "Style: Lessons in Clarity and Grace." Pearson Schweiz Ag (2014). 下载地址：https://pan.baidu.com/s/1cH26v0 目录：第一部分选择样式1 理解样式2 正确性第二部分清晰3 动作4 人物5 凝聚力和连贯性6 强调第三部

下载地址

github

原创 2022-07-15 21:24:29 204 阅读

Temporal Ensembling for Semi-Supervised Learning

Laine, Samuli, and Timo Aila. "Tem

迭代

github

数据

原创 2022-07-15 21:24:17 105 阅读

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

论文地址：https://128.84.21.19

百度

机器学习

github

原创 2022-07-15 21:23:52 21 阅读

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

作者提出的方法是Algotithm 2。简单来说就是，训练的时候，在几个模型中，选取预测最准确的（也就是loss最低的）模型进行权重更新。

权重

github

原创 2022-07-15 21:23:23 71 阅读

Boosting with Abstention

=

原始数据

github

权重

原创 2022-07-15 21:23:06 105 阅读

Tagger: Deep Unsupervised Perceptual Grouping

没看论文，但看

github

.net

原创 2022-07-15 21:22:58 15 阅读

Deep learning for Human Strategic Behaviour

没看，但是论文UI和视频做的很好。论文地址：https://papers.nips.cc/paper/6509-deep-learning-for-predicting-human-strategic-behavior.pdf 视频地址：https://www.youtube.com/watch?

github

原创 2022-07-15 21:22:34 108 阅读

Node Embedding

1.Kipf, Thomas N., and Max Welling. "Semi-supervised classification with graph convolutional networks." arXiv preprint arXiv:1609.02907 (2016). 2.Deff

sed

梯度下降

非对称

原创 2022-07-15 21:22:06 30 阅读

Layer Normalization

Ba, Jimmy Lei, Jamie Ryan Kiros, and Geoffrey E. Hinton. "Layer normalization." arXiv preprint arXiv:1607.06450 (2016). Batch Normalization是对每个神经元做归一化

github

归一化

数据

原创 2022-07-15 16:52:28 179 阅读

Using Fast Weights to Attend to the Recent Past

Ba, Jimmy, et al. "Using Fast Weights to Attend to the Recent Past." Advances In Neural Information Processing Systems. 2016. 感觉就是引入了memory的机制，多了一个矩阵A

github

数据

迭代

原创 2022-07-15 16:52:15 18 阅读

AI for AI

1.Li, Ke, and Jitendra Malik. "Learning to optimize." arXiv preprint arXiv:1606.01885 (2016). 2.Learning to Optimize Neural Nets link:https://arxiv.or

github

原创 2022-07-15 16:51:35 204 阅读

RL for Robots

1.Robot gains Social Intelligence through Multimodal Deep Reinforcement Learning 这篇文章使用DQN去训练一个机器人，使其能够模仿人类的交际。作者认为可以通过多模态学习来提高性能，作者用了灰度图和深度图分别训练两个神经网

神经网络

模态

github

原创 2022-07-15 16:51:27 68 阅读

官方博客	全部文章	热门标签	班级博客
了解我们	网站地图	意见反馈

鸿蒙开发者社区	51CTO学堂
51CTO	软考资讯

51CTO博客

wx62d12289ce45b的博客

Bitcoin: A Peer-to-Peer Electronic Cash System（比特币论文翻译）

GAN（Generative Adversarial Nets）的发展

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

Geometric deep learning on graphs and manifolds using mixture model CNNs

Semi-Supervised Classification with Graph Convolutional Networks

GRAPH ATTENTION NETWORKS

Generalization and Equilibrium in Generative Adversarial Nets

Learning to act by predicting the future

DSSM(DEEP STRUCTURED SEMANTIC MODELS)

The Properties of Posterior of Topic Model

Papers of Word Embeddings

Style Lessons in Clarity and Grace (11th Edition)中文翻译

Temporal Ensembling for Semi-Supervised Learning

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

Boosting with Abstention

Tagger: Deep Unsupervised Perceptual Grouping

Deep learning for Human Strategic Behaviour

Node Embedding

Layer Normalization

Using Fast Weights to Attend to the Recent Past

AI for AI

RL for Robots

欢迎