文档章节

人工智能资料库:第35辑(20170217)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:18
字数 406
阅读 0
收藏 0

  1. 【博客】Hello, Gradient Descent

简介:


Hi there! This article is part of a series called “Hello, <algorithm>”. In this series we will give some insights about how different AI algorithms work, and we will have fun by implementing them. Today we are gonna talk about Gradient Descent, a simple but yet powerful optimization algorithm for finding the (local) minimum of a given function.

原文链接:https://medium.com/ai-society/hello-gradient-descent-ef74434bdfa5#.ffcmstu3x


2.【论文 & 博客】Variational auto-encoder for "Frey faces" using keras

简介:

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions is two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.

原文链接:http://dohmatob.github.io/research/2016/10/22/VAE.html

论文链接:https://arxiv.org/pdf/1312.6114.pdf


3.【视频】Interactive Learning

简介:


原文链接:https://simons.berkeley.edu/workshops/schedule/3749


4.【代码】Code for Tensorflow Machine Learning Cookbook

简介:

Ch 1: Getting Started with TensorFlow
Ch 2: The TensorFlow Way
Ch 3: Linear Regression
Ch 4: Support Vector Machines
Ch 5: Nearest Neighbor Methods
Ch 6: Neural Networks
Ch 7: Natural Language Processing
Ch 8: Convolutional Neural Networks
Ch 9: Recurrent Neural Networks
Ch 10: Taking TensorFlow to Production
Ch 11: More with TensorFlow

原文链接:https://github.com/nfmcclure/tensorflow_cookbook


5.【博客】Recurrent Neural Networks for Beginners

简介:

In this post I discuss the basics of Recurrent Neural Networks (RNNs) which are deep learning models that are becoming increasingly popular. I don’t intend to get too heavily into the math and proofs behind why these work and am aiming for a more abstract understanding.

原文链接:https://medium.com/@camrongodbout/recurrent-neural-networks-for-beginners-7aca4e933b82#.spi0ozxux


本文转载自:http://www.jianshu.com/p/dd2805e4584d

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】20170217

20170216问题解析请点击今日问题下方的“【Java每日一题】20170217”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序输出结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/17
0
0
【Java每日一题】20170220

20170217问题解析请点击今日问题下方的“【Java每日一题】20170220”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序输出结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/20
0
0
2017中国人工智能产品经理大会

Be Changed or Make changes 未来已来! 我们正在从互联网时代跨入AI 时代, 一切正在被快速改变…… 同样,包括我们! 被改变,或作出改变…… 参加“AIPM Con 2017”, 打开互联网PM转型A...

活动家
2017/09/12
2
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
宿华:帮助中国人记录生活|“35岁以下科技创新35人”中国榜单专栏

  自 1999 年起,《麻省理工科技评论》每年都会推出“35岁以下创新35人”(Innovators Under 35)榜单,旨在于全球范围内评选出被认为最有才华、最具创新精神,以及最有可能改变世界的 35...

DeepTech深科技
05/03
0
0

没有更多内容

加载失败,请刷新页面

加载更多

window下安装maven

1.下载软件包: 2.解压到当前的安装路径: D:\Maven3.5.3 3.添加环境变量: 新建一个名为:MAVEN_HOME 填写解压路径:D:\Maven3.5.3 打开path,添加:%MAVEN_HOME%\bin 确定即可。 4.验证环境...

狼王黄师傅
7分钟前
0
0
聊聊flink的FsCheckpointStorage

序 本文主要研究一下flink的FsCheckpointStorage CheckpointStorage flink-runtime_2.11-1.7.0-sources.jar!/org/apache/flink/runtime/state/CheckpointStorage.java /** * CheckpointStor......

go4it
30分钟前
2
0
makefile 常用函数

Linux 环境下的程序员如果不会使用GNU make来构建和管理自己的工程,应该不能算是一个合格的专业程序员,至少不能称得上是 Unix程序员。今天我们来学习下makefile的常用函数。 《GNU make》h...

科陆李明
今天
17
0
Android 报错 Could not find com.android.tools.build:aapt2:3.2.1-4818971.

报错信息: Could not find com.android.tools.build:aapt2:3.2.1-4818971.Searched in the following locations: file:/C:/Users/96110/AppData/Local/Android/Sdk/extras/m2reposito......

lanyu96
今天
9
0
我的Linux系统九阴真经

我的Linux系统九阴真经 在今天,互联网的迅猛发展,科技技术也日新月异,各种编程技术也如雨后春笋一样,冒出尖来了。各种创业公司也百花齐放百家争鸣,特别是针对服务行业,新型互联网服务行...

linuxCool
今天
34
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