文档章节

人工智能资料库:第66辑(20170830)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:26
字数 477
阅读 5
收藏 0

1.【博客】Neural Nets for Generating Music

简介:

Algorithmic music composition has developed a lot in the last few years, but the idea has a long history. In some sense, the first automatic music came from nature: Chinese windchimes, ancient Greek wind-powered Aeolian harps, or the Japanese water instrument suikinkutsu. But in the 1700s music became “algorithmic”: Musikalisches Würfelspiel, a game that generates short piano compositions from fragments, with choices made by dice.

原文链接:https://medium.com/artists-and-machine-intelligence/neural-nets-for-generating-music-f46dffac21c0


  1. 【数据集】Fashion-MNIST

简介:

A dataset of Zalando's article images consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. Fashion-MNIST
is intended to serve as a direct drop-in replacement of the original MNIST dataset for benchmarking machine learning algorithms.

Here is an example how the data looks like (each class takes three-rows):


原文链接:https://github.com/zalandoresearch/fashion-mnist/blob/master/README.md


3.【论文】k-Nearest Neighbor Augmented Neural Networks for Text Classification

简介:

In recent years, many deep-learning based models are proposed for text classification. This kind of models well fits the training set from the statistical point of view. However, it lacks the capacity of utilizing instance-level information from individual instances in the training set. In this work, we propose to enhance neural network models by allowing them to leverage information from k-nearest neighbor (kNN) of the input text. Our model employs a neural network that encodes texts into text embeddings. Moreover, we also utilize k-nearest neighbor of the input text as an external memory, and utilize it to capture instance-level information from the training set. The final prediction is made based on features from both the neural network encoder and the kNN memory. Experimental results on several standard benchmark datasets show that our model outperforms the baseline model on all the datasets, and it even beats a very deep neural network model (with 29 layers) in several datasets. Our model also shows superior performance when training instances are scarce, and when the training set is severely unbalanced. Our model also leverages techniques such as semi-supervised training and transfer learning quite well.

原文链接:https://arxiv.org/pdf/1708.07863.pdf


4.【博客】Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp (Aug 2017)

简介:

From a talk given by John Schulman titled "The Nuts and Bolts of Deep RL Research" (Aug 2017)These are tricks written down while attending summer Deep RL Bootcamp at UC Berkeley.

原文链接:https://github.com/williamFalcon/DeepRLHacks


5.【代码】Collection of generative models in Tensorflow

简介:

Tensorflow implementation of various GANs and VAEs.


原文链接:https://github.com/hwalsuklee/tensorflow-generative-model-collections


本文转载自:http://www.jianshu.com/p/a0403039305b

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
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
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
这里有一份价值 800 美元的大礼包等你拿!区块链小伙伴进

惊喜小问卷, 大奖等你拿! 懂区块链的朋友,机会来了。长按或扫描下方二维码,填写我们的调研小问卷(1分钟)就有机会获得价值800美元的全球区块链峰会门票一张!世界顶级演讲,行业大咖云集...

硅谷密探
09/18
0
0
2018第四范式人工智能+新媒体论坛

2018首届人工智能+新媒体峰会将于11月6日在Blue Note Beijing举办。人民日报新媒体中心丁伟、原新华社新媒体中心总经理现中国搜索党委书记李俊、罗辑思维联合创始人李俊、凤凰新媒体客户端总...

第四范式
10/25
0
0

没有更多内容

加载失败,请刷新页面

加载更多

Nginx-使用简单总结

下载nginx:http://nginx.org/en/download.html 下载后解压 有很多种方法启动nginx (1)直接双击nginx.exe, 双击后一个黑色的弹窗一闪而过 (2)打开cmd命令窗口,切换到nginx解压目录下, 输入...

Java搬砖工程师
15分钟前
3
0
通过修改控制文件scn推进数据库scn

在数据库遇到ora-600[2662],scn不一致(又没有日志)的时候,我们首先想到的就是去推进数据库的scn,让数据库能够open起来,抢救其中的数据,但是由于各种乱用的情况,oraclescn的pach出来后(11.2...

突突突酱
16分钟前
1
0
Underscore _.template 方法使用详解

https://github.com/hanzichi/underscore-analysis/issues/26 前文 浅谈 Web 中前后端模板引擎的使用 我们简单了解了模板引擎在前后端的应用场景,本文重点深入 Underscore 的模板函数 _.te...

壹峰
17分钟前
1
0
前端缩短数字的长度解决方案[10进制转化为64进制]

function string10to64 (number) { var chars = '0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz_$'.split(''), radix = chars.length, qutient =......

未来cc
17分钟前
1
0
十年架构师不到400行手写一个Spring MVC

首先,我们先来介绍一下Spring的三个阶段,配置阶段、初始化阶段和运行阶段(如图): 配置阶段:主要是完成application.xml配置和Annotation配置。 初始化阶段:主要是加载并解析配置信息,...

小刀爱编程
18分钟前
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