文档章节

人工智能资料库:第62辑(20170617)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:26
字数 641
阅读 1
收藏 0
点赞 0
评论 0

1.【博客】Playing a toy poker game with Reinforcement Learning

简介:

Reinforcement learning (RL) has had some high-profile successes lately, e.g. AlphaGo, but the basic ideas are fairly straightforward. Let’s try RL on our favorite toy problem: the heads-up no limit shove/fold game. This is a pedagogical post rather than a research write-up, so we’ll develop all of the ideas (and code!) more or less from scratch. Follow along in a Python3 Jupyter notebook!

原文链接:http://willtipton.com/coding/poker/2017/06/06/shove-fold-with-reinforcement-learning.html


2.【论文】SuperSpike: Supervised learning in multi-layer spiking neural networks

简介:

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in-vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in-silico. Here we revisit the problem of supervised learning in temporally coding multi-layer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike-time patterns.

原文链接:https://arxiv.org/pdf/1705.11146.pdf


3.【博客】What Can't Deep Learning Do?

简介:

1/ What can’t deep learning do? Worth putting together a list of known failures to guide algorithmic development.

2/ Deep learning methods are known to fail at learning after small jitters to input. Think object recognition breaking when colors are swapped.

3/ Gradient based learning is quite slow. Takes many, many gradient descent steps to pick up patterns. Tough for high dimensional prediction.

4/ Deep learning methods are terrible at handling constraints. Not possible to find solutions satisfying constraints unlike linear programming.

5/ Training for complex models is quite unstable. Neural turing machines and GANs often don’t train well, with heavy dependence on rand seed.

......

原文链接:http://rbharath.github.io/what-cant-deep-learning-do/


4.【博客】8 Benefits of Customer Service Chatbots

简介:


We have all experienced the benefits and convenience of getting things done with just a tap on our phones. In today’s on-demand economy, our consumer expectations are higher than ever. If we don’t find answers or a resolution to our problems right away, we can easily move to the next brand. As a result, customer service departments play a key role for client retention and customer brand loyalty.

原文链接:https://blog.azumo.co/8-benefits-of-customer-service-chatbots-8c1b32e04096


5.【博客】Real-Time Stable Style Transfer for Videos

简介:

The paper A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge presents a technique for learning a style and applying it to other images. When used frame-by-frame on movies, the resulting stylized animations are of low quality. They suffer from extensive “popping”. We refer to popping as stylization features that are inconsistent from frame to frame. The stylized features (lines, strokes, colors) are present one frame but gone the next frame. The ‘artistic style transfer for videos’ video clearly shows the popping.

原文链接:https://elementai.github.io/research/2017/04/05/stable-style-transfer.html


本文转载自:http://www.jianshu.com/p/04cac8de7308

共有 人打赏支持
AllenOR灵感
粉丝 10
博文 2139
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

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

区块链技术让科学家共享患者健康资讯,同时保障个人资料安全

【Technews科技新报】目前医生在依据乳房摄影判断乳癌发生的情况下,有四分之一的乳癌无法被及时判断发现。为了提升乳癌确诊的效率,科学家计划以数百万包含了健康女性以及患有乳癌的女性乳房...

黄 斯沛 ⋅ 04/16 ⋅ 0

人工智能、大数据、复杂系统学习

黑科技,人工智能前进之路势不可挡! “做大做强新兴产业集群,实施大数据发展行动,加强新一代人工智能研发应用。发展智能产业,拓展智能生活。” 人工智能已作为国家乃至全球新的经济增长动...

自学号 ⋅ 05/10 ⋅ 0

人工智能时代的工作、学习和生活---《人工智能》阅读笔记

自从“罗辑思维”栏目从优酷网站搬到得到APP并且变为每天几分钟的节目之后,我就很少收听它了。某天,我打开得到APP,并且点开了“罗辑思维”的节目清单,发现有一期的标题包含了“人工智能”...

zhouzxi ⋅ 2017/07/15 ⋅ 0

人工智能有“天花板” 传统产业要“+科技”——知名企业家激战“新经济”

(原标题:人工智能有“天花板” 传统产业要“+科技”——知名企业家激战“新经济”) 中国证券网讯 据新华社12月5日消息,“携手新时代,共话新经济”,第四届世界互联网大会上,多位企业家...

上海证券报·中国证券网 ⋅ 2017/12/05 ⋅ 0

MongoDB 数据库不设防,意外泄露 3100 万用户信息

  IT 从业者 Kromtech 近日发现一个允许任何人存取的 MongoDB 资料库,内含 577GB 的资源,涉及 3100 万名 ai.type 的 Android 用户资料,其中包括用户姓名、电话号码、手机型号、通讯联络...

大数据头条 ⋅ 2017/12/11 ⋅ 0

科学家说:AI有加强现存偏见的可能

桑斯坦在《网络共和国》当中提出了算法影响我们的认知世界、并在《信息乌托邦》当中第一次明确提出了算法使人形成“信息茧房”的危害。这是算法对于人脑的影响,而算法应用于人工智能中,也让...

玄学酱 ⋅ 04/13 ⋅ 0

AI不是魔法:人工智能的能与不能

  本文作者将从四类具体应用的实现上,看看AI技术给我们生活带来哪些便利,以及存在哪些局限?enjoy~      如果把AI技术分为「前端的交互技术」和「后端的人工智能技术」。前端的交互技...

深度学习 ⋅ 05/28 ⋅ 0

MongoDB 数据库不设防,意外泄露 3100 万用户信息

IT 从业者 Kromtech 近日发现一个允许任何人存取的 MongoDB 资料库,内含 577GB 的资源,涉及 3100 万名 ai.type 的 Android 用户资料,其中包括用户姓名、电话号码、手机型号、通讯联络人等...

达尔文 ⋅ 2017/12/11 ⋅ 16

没有更多内容

加载失败,请刷新页面

加载更多

下一页

Springboot2 之 Spring Data Redis 实现消息队列——发布/订阅模式

一般来说,消息队列有两种场景,一种是发布者订阅者模式,一种是生产者消费者模式,这里利用redis消息“发布/订阅”来简单实现订阅者模式。 实现之前先过过 redis 发布订阅的一些基础概念和操...

Simonton ⋅ 34分钟前 ⋅ 0

error:Could not find gradle

一.更新Android Studio后打开Project,报如下错误: Error: Could not find com.android.tools.build:gradle:2.2.1. Searched in the following locations: file:/D:/software/android/andro......

Yao--靠自己 ⋅ 昨天 ⋅ 0

Spring boot 项目打包及引入本地jar包

Spring Boot 项目打包以及引入本地Jar包 [TOC] 上篇文章提到 Maven 项目添加本地jar包的三种方式 ,本篇文章记录下在实际项目中的应用。 spring boot 打包方式 我们知道,传统应用可以将程序...

Os_yxguang ⋅ 昨天 ⋅ 0

常见数据结构(二)-树(二叉树,红黑树,B树)

本文介绍数据结构中几种常见的树:二分查找树,2-3树,红黑树,B树 写在前面 本文所有图片均截图自coursera上普林斯顿的课程《Algorithms, Part I》中的Slides 相关命题的证明可参考《算法(第...

浮躁的码农 ⋅ 昨天 ⋅ 0

android -------- 混淆打包报错 (warning - InnerClass ...)

最近做Android混淆打包遇到一些问题,Android Sdutio 3.1 版本打包的 错误如下: Android studio warning - InnerClass annotations are missing corresponding EnclosingMember annotation......

切切歆语 ⋅ 昨天 ⋅ 0

eclipse酷炫大法之设置主题、皮肤

eclipse酷炫大法 目前两款不错的eclipse 1.系统设置 Window->Preferences->General->Appearance 2.Eclipse Marketplace下载【推荐】 Help->Eclipse Marketplace->搜索‘theme’进行安装 比如......

anlve ⋅ 昨天 ⋅ 0

vim编辑模式、vim命令模式、vim实践

vim编辑模式 编辑模式用来输入或修改文本内容,编辑模式除了Esc外其他键几乎都是输入 如何进入编辑模式 一般模式输入以下按键,均可进入编辑模式,左下角提示 insert(中文为插入) 字样 i ...

蛋黄Yolks ⋅ 昨天 ⋅ 0

大数据入门基础:SSH介绍

什么是ssh 简单说,SSH是一种网络协议,用于计算机之间的加密登录。 如果一个用户从本地计算机,使用SSH协议登录另一台远程计算机,我们就可以认为,这种登录是安全的,即使被中途截获,密码...

董黎明 ⋅ 昨天 ⋅ 0

web3j教程

web3j是一个轻量级、高度模块化、响应式、类型安全的Java和Android类库提供丰富API,用于处理以太坊智能合约及与以太坊网络上的客户端(节点)进行集成。 汇智网最新发布的web3j教程,详细讲解...

汇智网教程 ⋅ 昨天 ⋅ 0

谷歌:安全问题机制并不如你想象中安全

腾讯科技讯 5月25日,如今的你或许已经对许多网站所使用的“安全问题机制”习以为常了,但你真的认为包括“你第一个宠物的名字是什么?”这些问题能够保障你的帐户安全吗? 根据谷歌(微博)安...

问题终结者 ⋅ 昨天 ⋅ 0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

返回顶部
顶部