文档章节

人工智能资料库:第9辑(20170113)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:26
字数 753
阅读 2
收藏 0

  1. 【论文集】The classical papers and codes about generative adversarial nets

简介:

这是一个关于生成对抗网络的经典论文和代码集。

原文链接:https://github.com/zhangqianhui/AdversarialNetsPapers


2.【博客】Deep Learning Paper Implementations: Spatial Transformer Networks - Part I

简介:

The first three blog posts in my “Deep Learning Paper Implementations” series will cover Spatial Transformer Networks introduced by Max Jaderberg, Karen Simonyan, Andrew Zisserman and Koray Kavukcuoglu of Google Deepmind in 2016. The Spatial Transformer Network is a learnable module aimed at increasing the spatial invariance of Convolutional Neural Networks in a computationally and parameter efficient manner.


原文链接:https://kevinzakka.github.io/2017/01/10/stn-part1/


3.【博客】GTA V + Universe

简介:

The Universe integration with Grand Theft Auto V, built and maintained by Craig Quiter's DeepDrive project, is now open-source. To use it, you'll just need a purchased copy of GTA V, and then your Universe agent will be able to start driving a car around the streets of a high-fidelity virtual world.

GTA V in Universe gives AI agents access to a rich, 3D world. This video shows the frames fed to the agent (artificially slowed to 8FPS, top left), diagnostics from the agent and environment (bottom left), and a human-friendly free camera view (right). The integration modifies the behavior of people within GTA V to be non-violent.

原文链接:https://openai.com/blog/GTA-V-plus-Universe/


4.【论文&代码】Learning Python Code Suggestion with a Sparse Pointer Network

简介:

To enhance developer productivity, all modern integrated development environments(IDEs) include code suggestion functionality that proposes likely next tokens at the cursor. While current IDEs work well for statically-typed languages, their reliance on type annotations means that they do not provide the same level of support for dynamic programming languages as for statically-typed languages. Moreover, suggestion engines in modern IDEs do not propose expressions or multi-statement idiomatic code. Recent work has shown that language models can improve code suggestion systems by learning from software repositories. This paper introduces a neural language model with a sparse pointer network aimed at capturing very longrange dependencies. We release a large-scale code suggestion corpus of 41M lines of Python code crawled from GitHub. On this corpus, we found standard neural language models to perform well at suggesting local phenomena, but struggle to refer to identifiers that are introduced many tokens in the past. By augmenting a neural language model with a pointer network specialized in referring to predefined classes of identifiers, we obtain a much lower perplexity and a 5 percentage points increase in accuracy for code suggestion compared to an LSTM baseline. In fact, this increase in code suggestion accuracy is due to a 13 times more accurate prediction of identifiers. Furthermore, a qualitative analysis shows this model indeed captures interesting long-range dependencies, like referring to a class member defined over 60 tokens in the past.

原文链接:https://arxiv.org/pdf/1611.08307v1.pdf

代码链接:https://github.com/uclmr/pycodesuggest


5.【论文&代码】 StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

简介:

Synthesizing photo-realistic images from text descriptions is a challenging problem in computer vision and has many practical applications. Samples generated by existing text-to-image approaches can roughly reflect the meaning of the given descriptions, but they fail to contain necessary details and vivid object parts. In this paper, we propose stacked Generative Adversarial Networks (StackGAN) to generate photo-realistic images conditioned on text descriptions. The Stage-I GAN sketches the primitive shape and basic colors of the object based on the given text description, yielding Stage-I low resolution images. The Stage-II GAN takes Stage-I results and text descriptions as inputs, and generates high resolution images with photorealistic details. The Stage-II GAN is able to rectify defects and add compelling details with the refinement process. Samples generated by StackGAN are more plausible than those generated by existing approaches. Importantly, our StackGAN for the first time generates realistic 256 × 256 images conditioned on only text descriptions, while state-of-the-art methods can generate at most 128 × 128 images. To demonstrate the effectiveness of the proposed StackGAN, extensive experiments are conducted on CUB and Oxford-102 datasets, which contain enough object appearance variations and are widely-used for text-toimage generation analysis.

原文链接:https://arxiv.org/pdf/1612.03242v1.pdf

代码链接:https://github.com/hanzhanggit/StackGAN


本文转载自:http://www.jianshu.com/p/83b16051b1a2

共有 人打赏支持
AllenOR灵感
粉丝 10
博文 2634
码字总数 82983
作品 0
程序员
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0
MAC 修改虚拟主机,列举所有文件和目录

20180604 在新的 macbook 上,重设虚拟目录 1、直接采用系统缺省的 localhost,目录位置: DocumentRoot "/Library/WebServer/Documents" <Directory "/Library/WebServer/Documents"> 2、h......

wwzzhh166
2017/01/13
0
0
【Java每日一题】20170113

20170112问题解析请点击今日问题下方的“【Java每日一题】20170113”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序能否正常编译通过?(点击以下“【Java每日一...

weknow
2017/01/13
0
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0
AI一分钟 | 微软将成立微软亚洲研究院上海分院;阿里AI鉴黄师能判别呻吟声

▌京东金融更名“京东数科”,官方:更体现公司定位 “京东金融”官方微博、头条、抖音于 17 日晚间更改名称为“京东数科”。就此,京东金融回应称:“我们认为数字科技更能体现公司的定位,...

AI科技大本营
09/18
0
0

没有更多内容

加载失败,请刷新页面

加载更多

Web系统大规模并发:电商秒杀与抢购

一、大规模并发带来的挑战 在过去的工作中,我曾经面对过5w每秒的高并发秒杀功能,在这个过程中,整个Web系统遇到了很多的问题和挑战。如果Web系统不做针对性的优化,会轻而易举地陷入到异常...

xtof
今天
2
0
代码质量管理平台-sonarqube

在工作中,往往开发的时候会不怎么注重代码质量的人很多,存在着很多的漏洞和隐患等问题,sonarqube可以进行代码质量的审核,而且十分的残酷。。。。。接下来我们说下怎么安装 进入官网下载:...

落叶清风
今天
7
0
在Ubuntu安装和配置Sphinx

Ubuntu系统默认是配置有sphinx的,先检查一下,别多此一举。。。。。 在开始本指南之前,您需要: 一个Ubuntu 16.04服务器。 sudo的一个非root用户,您可以通过以下设置本教程 。 安装在服务...

阿锋zxf
今天
3
0
Qt编写输入法V2018超级终结版

对于qt嵌入式linux开发人员来说,输入法一直是个鸡肋问题,要么不支持实体键盘同步,要么不能汉字输入,要么不支持网页输入等,这几年通过陆续接触大量的各种输入法应用场景客户,得到真实需...

飞扬青云
今天
2
0
TypeScript基础入门之高级类型的多态的 this类型

转发 TypeScript基础入门之高级类型的多态的 this类型 高级类型 多态的this类型 多态的this类型表示的是某个包含类或接口的子类型。 这被称做F-bounded多态性。 它能很容易的表现连贯接口间的...

durban
今天
0
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部