请选择 进入手机版 | 继续访问电脑版

技术控

    今日:187| 主题:53563
收藏本版 (1)
最新软件应用技术尽在掌握

[其他] DeepMind’s new computer can navigate London’s Underground using memory

[复制链接]
香樟 发表于 2016-10-15 06:40:23
270 2

立即注册CoLaBug.com会员,免费获得投稿人的专业资料,享用更多功能,玩转个人品牌!

您需要 登录 才可以下载或查看,没有帐号?立即注册

x

DeepMind’s new computer can navigate London’s Underground using memory

DeepMind’s new computer can navigate London’s Underground using memory

    DeepMind, the AI research firm that is owned by Google’s parent company Alphabet , has created a computer that can learn and accomplish tasks from its own memory. The computer uses a neural network that can  store and recall facts. This allows it to, for example, find the best route from one point to another on London’s famed Underground subway without any prior programming.
   

DeepMind’s new computer can navigate London’s Underground using memory

DeepMind’s new computer can navigate London’s Underground using memory
   Previously: Go champion of the world wants a piece of Google’s DeepMind AI     3      DeepMind calls its newest project the differentiable neural computer.  Here’s a very quick description of how it works:
  When we designed DNCs, we wanted machines that could learn to form and navigate complex data structures on their own. At the heart of a DNC is a neural network called a controller, which is analogous to the processor in a computer. A controller is responsible for taking input in, reading from and writing to memory, and producing output that can be interpreted as an answer. The memory is a set of locations that can each store a vector of information.
   

DeepMind’s new computer can navigate London’s Underground using memory

DeepMind’s new computer can navigate London’s Underground using memory

  Over time this controller can come up with better answers to questions by using its memory.  One experiment used the map layout of the London Underground as its basis:
  When we described the stations and lines of the London Underground, we could ask a DNC to answer questions like, “Starting at Bond street, and taking the Central line in a direction one stop, the Circle line in a direction for four stops, and the Jubilee line in a direction for two stops, at what stop do you wind up?” Or, the DNC could plan routes given questions like “How do you get from Moorgate to Piccadilly Circus?”
  DeepMind’s new computer can also figure out relationships in a family tree with the same learning and memory method, along with solving puzzles. The AI firm hopes that development of DNCs will only create better computers but might also help in finding out how memory works in humans as well.



上一篇:Books Programmers Don't Really Read (2008)
下一篇:传输层安全协议抓包分析之SSL/TLS
zy_workjob 发表于 2016-10-16 08:51:13
楼主,么么哒!
回复 支持 反对

使用道具 举报

hsimy 发表于 2016-11-18 23:41:52
楼主辛苦了,鼓励一下
回复 支持 反对

使用道具 举报

*滑动验证:
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

我要投稿

推荐阅读

扫码访问 @iTTTTT瑞翔 的微博
回页顶回复上一篇下一篇回列表
手机版/CoLaBug.com ( 粤ICP备05003221号 | 文网文[2010]257号 )

© 2001-2017 Comsenz Inc. Design: Dean. DiscuzFans.

返回顶部 返回列表