[转] Computer science: The learning machines - webdancer's Blog

[转] Computer science: The learning machines

webdancer posted @ 2014年1月09日 04:31 in 未分类 with tags Machine learning , 1247 阅读

文章链接:http://www.nature.com/news/computer-science-the-learning-machines-1.14481

Using massive amounts of data to recognize photos and speech, deep-learning computers are taking a big step towards true artificial intelligence.

Three years ago, researchers at the secretive Google X lab in Mountain View, California, extracted some 10 million still images from YouTube videos and fed them into Google Brain — a network of 1,000 computers programmed to soak up the world much as a human toddler does. After three days looking for recurring patterns, Google Brain decided, all on its own, that there were certain repeating categories it could identify: human faces, human bodies and … cats1.

介绍了 Deep  learning的最新 的一些 进展,简单的总结一下:

  • Google  Brain Project(10^6神经元,10^9连接)代表的Deep learning技术让神经网络复兴;
  • Neural Networks(神经网络)模仿人脑的神经元连接,通过经验来更改连接的强度,模拟人类的学习;
  • 神经网络可以用来识别图像,处理自然语言,语音识别,翻译语言等;
  • AI的历史:
    • 50s:手工提取特征,费事耗力;
    • 80-90s:浅层网络“Neural nets were always a delicate art to manage. There is some black magic involved,”
    • 2000s:计算能力的增强和数据的爆炸式增长;“For about US$100,000 in hardware, we can build an 11-billion-connection network, with 64 GPUs,” 
  • 现在 Deep  Learning在 语音识别(25%), 图像 识别(ImageNet, 15%),下一步在NLP

 

Charlie Northey 说:
2018年10月22日 01:17

The learning machines are very good for their users and offer vast range of features for the help of their users. Online writing companies provide writers to help me with my assignment work and charge reasonable fee.


登录 *


loading captcha image...
(输入验证码)
or Ctrl+Enter
Host by is-Programmer.com | Power by Chito 1.3.3 beta | © 2007 LinuxGem | Design by Matthew "Agent Spork" McGee