文档章节

人工智能资料库:第39辑(20170223)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:27
字数 629
阅读 1
收藏 0

  1. 【博客 & 视频】Why Medicine Needs Deep Learning

简介:


Deep learning will transform medicine, but not in the way that many advocates think. The amount of data times the mutation frequency divided by the biological complexity and the number of hidden variables is small, so downloading a hundred thousand genomes and training a neural network won’t cut it.

原文链接:http://artificialbrain.xyz/why-medicine-needs-deep-learning/


2.【博客】Read-through: Wasserstein GAN

简介:

For Wasserstein GAN, it was mostly compelling word of mouth.

  • The paper proposes a new GAN training algorithm that works well on the common GAN datasets.

  • Said training algorithm is backed up by theory. In deep learning, not all theory-justified papers have good empirical results, but theory-justified papers with good empirical results have really good empirical results. For those papers, it’s very important to understand their theory, because the theory usually explains why they perform so much better.

  • I heard that in Wasserstein GAN, you can (and should) train the discriminator to convergence. If true, it would remove needing to balance generator updates with discriminator updates, which feels like one of the big sources of black magic for making GANs train.

  • The paper shows a correlation between discriminator loss and perceptual quality. This is actually huge if it holds up well. In my limited GAN experience, one of the big problems is that the loss doesn’t really mean anything, thanks to adversarial training, which makes it hard to judge if models are training or not. Reinforcement learning has a similar problem with its loss functions, but there we at least get mean episode reward. Even a rough quantitative measure of training progress could be good enough to use automated hyperparam optimization tricks, like Bayesian optimization. (See this post and this post for nice introductions to automatic hyperparam tuning.)

原文链接:http://www.alexirpan.com/2017/02/22/wasserstein-gan.html?utm_content=buffer7f258&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer


3.【demo & 代码】Image-to-Image Demo

简介:


Recently, I made a Tensorflow port of pix2pix by Isola et al., covered in the article Image-to-Image Translation in Tensorflow. I've taken a few pre-trained models and made an interactive web thing for trying them out. Chrome is recommended.

The pix2pix model works by training on pairs of images such as building facade labels to building facades, and then attempts to generate the corresponding output image from any input image you give it. The idea is straight from the pix2pix paper, which is a good read.

原文链接:http://affinelayer.com/pixsrv/index.html


4.【博客】Sorting through the tags: how does Tumblr’s graph-based topic modeling work?

简介:


What makes Tumblr stand apart from other social media platforms lies in the unique way its users communicate with each other. Each user has their own highly customizable blog where they can post and share content — like articles, images, GIFs, or videos — or re-post content published by another user. Sharing and re-posting content is not only key to how social connections are formed, but also how trending and popular topics are established, since the user must tag each post that they publish.

原文链接:https://medium.com/@NYUDataScience/sorting-through-the-tags-how-does-tumblrs-graph-based-topic-modeling-work-1d396fb48f54#.fay5h8act


5.【博客 & 代码】How to implement Sentiment Analysis using word embedding and Convolutional Neural Networks on Keras.

简介:

Imdb has released a database of 50,000 movie reviews classified in two categories: Negative and Positive. This is a typical sequence binary classification problem.

In this article, I will show how to implement a Deep Learning system for such sentiment analysis with ~87% accuracy. (State of the art is at 88.89% accuracy).

原文链接:https://medium.com/@thoszymkowiak/how-to-implement-sentiment-analysis-using-word-embedding-and-convolutional-neural-networks-on-keras-163197aef623#.sq6ax02mg


本文转载自:http://www.jianshu.com/p/2fff505a8e9a

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】20170223

20170222问题解析请点击今日问题下方的“【Java每日一题】20170223”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序是否有编译错误?(点击以下“【Java每日一题...

weknow
2017/02/23
0
0
Redshift drop有依赖关系的表

今天开发需要删除AWS Redshift的一个归档表,但是直接drop发生了如下报错,发现有其他对象依赖这个表,导致无法直接删除,但是报错没有直接显示是什么对象依赖它,可能是有视图,外键等约束 ...

Darren_Chen
08/14
0
0
【Java每日一题】20170224

20170223问题解析请点击今日问题下方的“【Java每日一题】20170224”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序运行结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/24
0
0
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
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

没有更多内容

加载失败,请刷新页面

加载更多

Spring源码学习笔记-1-Resource

打算补下基础,学习下Spring源码,参考书籍是《Spring源码深度解析》,使用版本是Spring 3.2.x,本来想试图用脑图记录的,发现代码部分不好贴,还是作罢,这里只大略记录下想法,不写太细了 ...

zypy333
今天
10
0
RestClientUtil和ConfigRestClientUtil区别说明

RestClientUtil directly executes the DSL defined in the code. ConfigRestClientUtil gets the DSL defined in the configuration file by the DSL name and executes it. RestClientUtil......

bboss
今天
17
0

中国龙-扬科
昨天
2
0
Linux系统设置全局的默认网络代理

更改全局配置文件/etc/profile all_proxy="all_proxy=socks://rahowviahva.ml:80/"ftp_proxy="ftp_proxy=http://rahowviahva.ml:80/"http_proxy="http_proxy=http://rahowviahva.ml:80/"......

临江仙卜算子
昨天
10
0
java框架学习日志-6(bean作用域和自动装配)

本章补充bean的作用域和自动装配 bean作用域 之前提到可以用scope来设置单例模式 <bean id="type" class="cn.dota2.tpye.Type" scope="singleton"></bean> 除此之外还有几种用法 singleton:......

白话
昨天
10
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