文档章节

人工智能资料库:第11辑(20170117)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:20
字数 610
阅读 4
收藏 0

  1. 【论文&代码】Accelerating Eulerian Fluid Simulation With Convolutional Networks
    简介:

Real-time simulation of fluid and smoke is a long standing problem in computer graphics, where state-of-the-art approaches require large compute resources, making real-time applications often impractical. In this work, we propose a data-driven approach that leverages the approximation power of deep-learning methods with the precision of standard fluid solvers to obtain both fast and highly realistic simulations. The proposed method solves the incompressible Euler equations following the standard operator splitting method in which a large, often ill-condition linear system must be solved. We propose replacing this system by learning a Convolutional Network (ConvNet) from a training set of simulations using a semi-supervised learning method to minimize long-term velocity divergence.

ConvNets are amenable to efficient GPU implementations and, unlike exact iterative solvers, have fixed computational complexity and latency. The proposed hybrid approach restricts the learning task to a linear projection without modeling the well understood advection and body forces. We present real-time 2D and 3D simulations of fluids and smoke; the obtained results are realistic and show good generalization properties to unseen geometry.

原文链接:http://cims.nyu.edu/~schlacht/CNNFluids.htm

代码链接:https://github.com/google/FluidNet


2.【博客】Highway Networks with TensorFlow

简介:

This week I implemented highway networks to get an intuition for how they work. Highway networks, inspired by LSTMs, are a method of constructing networks with hundreds, even thousands, of layers. Let’s see how we construct them using TensorFlow.

原文链接:https://medium.com/jim-fleming/highway-networks-with-tensorflow-1e6dfa667daa#.vxxpgint3


3.【博客】An LSTM Odyssey

简介:

This week I read LSTM: A Search Space Odyssey. It’s an excellent paper that systematically evaluates the different internal mechanisms of an LSTM (long short-term memory) block by disabling each mechanism in turn and comparing their performance. We’re going to implement each of the variants in TensorFlow and evaluate their performance on the Penn Tree Bank (PTB) dataset. This will obviously not be as thorough as the original paper but it allows us to see, and try out, the impact of each variant for ourselves.

原文链接:https://medium.com/jim-fleming/implementing-lstm-a-search-space-odyssey-7d50c3bacf93#.7iqy02qh0


4.【博客&代码】Recurrent generative auto-encoders and novelty search

简介:

This post summarizes a bunch of connected tricks and methods I explored with the help of my co-authors. Following the previous post, above the stability properties of GANs, the overall aim was to improve our ability to train generative models stably and accurately, but we went through a lot of variations and experiments with different methods on the way. I’ll try to explain why I think these things worked, but we’re still exploring it ourselves as well.

原文链接:http://www.araya.org/archives/1306?utm_content=buffer1bcba&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer

代码链接:https://github.com/arayabrain/RecurrentAutoencoder


5.【博客&代码】Recursive (not recurrent!) Neural Nets in TensorFlow

简介:

For the past few days I’ve been working on how to implement recursive neural networks in TensorFlow. Recursive neural networks (which I’ll call TreeNets from now on to avoid confusion with recurrent neural nets) can be used for learning tree-like structures (more generally, directed acyclic graph structures). They are highly useful for parsing natural scenes and language; see the work of Richard Socher (2011) for examples. More recently, in 2014, Ozan İrsoy used a deep variant of TreeNets to obtain some interesting NLP results.

原文地址:https://pseudoprofound.wordpress.com/2016/06/20/recursive-not-recurrent-neural-nets-in-tensorflow/

代码地址:https://gist.github.com/anj1/504768e05fda49a6e3338e798ae1cddd


本文转载自:http://www.jianshu.com/p/f696814c2d55

共有 人打赏支持
AllenOR灵感
粉丝 11
博文 2635
码字总数 83001
作品 0
程序员
私信 提问
【Java每日一题】20170117

20170116问题解析请点击今日问题下方的“【Java每日一题】20170117”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? list泛型化参数是Integer和F...

weknow
2017/01/22
0
0
国行版HomePod售价2799元,本周五发售

(图片源自苹果中国官网截图) 整理 | 一一 出品 | AI科技大本营 去年 12 月,苹果表示将于今年年初在中国销售其 HomePod 智能音箱。1 月 14 日,苹果公司正式宣布,HomePod 将于 1 月 18 日...

AI科技大本营
01/14
0
0
人工智能资料库:第72辑(20171203)

1.【会议】Bayesian Deep Learning 简介: While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor......

chen_h
2017/12/03
0
0
【Java每日一题】20170118

20170117问题解析请点击今日问题下方的“【Java每日一题】20170118”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: Sub子类中的两个方法正确吗?(点击以下“【Java每日一题...

weknow
2017/01/22
0
0
依图夺脸部辨识首奖,施密特:美国 AI 优势只剩 5 年

Thomson Reuters 28 日报导,根据美国智库“新美国安全中心”(CNAS)专家 Elsa Kania 发布的报告,中国在科技领域已经不比美国差,可能已有能力在人工智能(AI)项目超越美国。 Alphabet I...

moneydj
2017/11/29
0
0

没有更多内容

加载失败,请刷新页面

加载更多

OSChina 周四乱弹 —— 我想过年请假提前回家两天

Osc乱弹歌单(2019)请戳(这里) 【今日歌曲】 @clouddyy :#每日一歌# 分享王力宏的单曲《爱错》 《爱错》- 王力宏 手机党少年们想听歌,请使劲儿戳(这里) @Caremorele :这几天起床有点...

小小编辑
27分钟前
7
1
Cookie 显示用户上次访问的时间

import javax.servlet.ServletException;import javax.servlet.annotation.WebServlet;import javax.servlet.http.Cookie;import javax.servlet.http.HttpServlet;import javax.serv......

gwl_
今天
1
0
网络编程

第14天 网络编程 今日内容介绍  网络通信协议  UDP通信  TCP通信 今日学习目标  能够辨别UDP和TCP协议特点  能够说出UDP协议下两个常用类名称  能够说出TCP协议下两个常用类名称...

stars永恒
今天
2
0
二进制相关

二进制 众所周知计算机使用的是二进制,数字的二进制是如何表示的呢? 实际就是逢二进一。比如 2 用二进制就是 10。那么根据此可以推算出 5的二进制等于 10*10+1 即为 101。 在计算机中,负数以...

NotFound403
昨天
3
0
day22:

1、写一个getinterface.sh 脚本可以接受选项[i,I],完成下面任务: 1)使用格式:getinterface.sh [-i interface | -I ip] 2)当用户使用-i选项时,显示指定网卡的IP地址;当用户使用-I选项...

芬野de博客
昨天
2
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