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

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 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
计算机科学家论文引用排名:LeCun终于晋身三巨头

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/yH0VLDe8VG8ep9VGe/article/details/82598742 问耕 发自 凹非寺 量子位 出品 | 公众号 QbitAI “我又来吹牛了...

量子位
09/09
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

http协议请求头的意义

GET /day31_Http_306/index.jsp HTTP/1.1: GET请求,请求服务器路径为/hello/index.jsp,协议为1.1 请求头 1.Host:localhost:请求的主机名为localhost2.User-Agent:Mozilla/5.0(Windows NT......

潇潇程序缘
34分钟前
6
0
Netty 简单服务器 (三)

经过对Netty的基础认识,设计模型的初步了解,来写个测试,试试手感 上篇也说到官方推荐我们使用主从线程池模型,那就选择这个模型进行操作 需要操作的步骤: 需要构建两个主从线程组 写一个服务器...

_大侠__
45分钟前
8
0
day02:管道符、shell及环境变量

1、管道符:"|" 用于将前一个指令的输出作为后一个指令的输入,且管道符后面跟的是命令(针对文档的操作):cat less head tail grep cut sort wc uniq tee tr split sed awk等) [root@localho...

芬野de博客
55分钟前
15
0
Kubernetes系列——Kubernetes 组件、对象(二)

一、Kubernetes 组件 介绍了Kubernetes集群所需的各种二进制组件。 Master 组件 Master组件提供集群的管理控制中心。Master组件可以在集群中任何节点上运行。但是为了简单起见,通常在一...

吴伟祥
今天
17
0
Flink-数据流编程模型

1、抽象等级 Flink提供了不同级别的抽象来开发流/批处理应用程序。 1) 低层级的抽象 最低层次的抽象仅仅提供有状态流。它通过Process函数嵌入到DataStream API中。它允许用户自由地处理来自一...

liwei2000
今天
15
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