A theory of the learnable

最新推荐文章于 2021-04-25 23:03:26 发布

原创最新推荐文章于 2021-04-25 23:03:26 发布 · 1.1k 阅读

0 ·

CC 4.0 BY-SA版权

Algorithm[paper] 专栏收录该内容

3 篇文章

订阅专栏

本文探讨了人类无需显式编程即可学习新概念的现象，并从计算角度给出了一种精确的研究方法。虽然算法复杂性对可学习的概念范围有所限制，但研究发现仍有一些重要的命题类概念能够在现实中被学习。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

[2013-5-28 pm] I have to read this paper because my paper for my graduation

A Theory of the Learnable

Abstract:

Humans appear to be able to learn new concepts without needing to be pogrammed explicitly in any coventional sense.In this paper we regard learning as the phenomenon of knowledge acquisition in the absence of explicit programming.We give a precise methodology for studying this phenomenon from a computational viewpoint. It consists of choosing an appropriate information gathering mechnism, the learning protocol, and ex

Although inherent algorithmic complexity appears to set serious limits to the range of concepts the can be learned, we show that there are some important nontrivial classes of propositional concepts that can be learned in a realistic sense.

人们似乎可以不需要任何传统支持就可以学习新的概念。在本文中，我们认为学习新支持不需要explicit programming. 我们给出了来自计算角度的的严格方法。

尽管算法固有的复杂性似乎限制了概念学习的范围，我们证明有一些重要的命题类概念在实际中可以被学习。