link.springer.com/article/10.1007/s10994-006-6265-7

Preview meta tags from the link.springer.com website.

Linked Hostnames

22

Thumbnail

Search Engine Appearance

Google

https://link.springer.com/article/10.1007/s10994-006-6265-7

An algorithmic theory of learning: Robust concepts and random projection - Machine Learning

We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples



Bing

An algorithmic theory of learning: Robust concepts and random projection - Machine Learning

https://link.springer.com/article/10.1007/s10994-006-6265-7

We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples



DuckDuckGo

https://link.springer.com/article/10.1007/s10994-006-6265-7

An algorithmic theory of learning: Robust concepts and random projection - Machine Learning

We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples

  • General Meta Tags

    120
    • title
      An algorithmic theory of learning: Robust concepts and random projection | Machine Learning
    • charset
      UTF-8
    • X-UA-Compatible
      IE=edge
    • applicable-device
      pc,mobile
    • viewport
      width=device-width, initial-scale=1

  • Open Graph Meta Tags

    6
    • og:url
      https://link.springer.com/article/10.1007/s10994-006-6265-7
    • og:type
      article
    • og:site_name
      SpringerLink
    • og:title
      An algorithmic theory of learning: Robust concepts and random projection - Machine Learning
    • og:description
      We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples despite the fact that each example contains a huge amount of information? We provide a novel algorithmic analysis via a model of robust concept learning (closely related to “margin classifiers”), and show that a relatively small number of examples are sufficient to learn rich concept classes. The new algorithms have several advantages—they are faster, conceptually simpler, and resistant to low levels of noise. For example, a robust half-space can be learned in linear time using only a constant number of training examples, regardless of the number of attributes. A general (algorithmic) consequence of the model, that “more robust concepts are easier to learn”, is supported by a multitude of psychological studies.

  • Twitter Meta Tags

    6
    • twitter:site
      @SpringerLink
    • twitter:card
      summary_large_image
    • twitter:image:alt
      Content cover image
    • twitter:title
      An algorithmic theory of learning: Robust concepts and random projection
    • twitter:description
      Machine Learning - We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples despite the fact that...

  • Item Prop Meta Tags

    3
    • position
      1
    • position
      2
    • position
      3

  • Link Tags

    9
    • apple-touch-icon
      /oscar-static/img/favicons/darwin/apple-touch-icon-6ef0829b9c.png
    • canonical
      https://link.springer.com/article/10.1007/s10994-006-6265-7
    • icon
      /oscar-static/img/favicons/darwin/android-chrome-192x192.png
    • icon
      /oscar-static/img/favicons/darwin/favicon-32x32.png
    • icon
      /oscar-static/img/favicons/darwin/favicon-16x16.png

Emails

1

Links

94