arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.00840cs.AIcs.NE
收藏

归纳、波普和机器学习

Induction, Popper, and machine learning

Bruce Nielson, Daniel C. Elton

摘要:

弗朗西斯·培根普及了这样一种观点,即科学是建立在归纳过程的基础上的,通过这种归纳过程,重复的观察以某种未指明的方式被概括为基于未来与过去相似的假设的理论。休谟和其他人批评这个观点是站不住脚的,导致了著名的归纳问题。直到卡尔·波普尔(Karl Popper)的工作才解决了这个问题,他证明了归纳不是科学的基础,科学知识的发展是基于与生物进化相同的原则。今天,机器学习也被教导为植根于大数据的归纳。在理想化贝叶斯代理(Hutter's AIXI)中实现的Solomonoff归纳被广泛讨论,并被吹捧为理解AI算法的框架,尽管现实世界中尝试实现像AIXI这样的东西会立即遇到致命的问题。在本文中,我们将基于归纳的框架与唐纳德·T.坎贝尔的普遍达尔文主义我们表明,当今使用的大多数AI算法都可以理解为使用进化的试错过程在解空间中搜索。在这项工作中,我们认为,一个通用的达尔文框架为理解人工智能系统提供了更好的基础。此外,在更Meta的层面上,所有AI算法的发展过程都可以在通用达尔文主义的框架下理解。

英文摘要:

Francis Bacon popularized the idea that science is based on a process of induction by which repeated observations are, in some unspecified way, generalized to theories based on the assumption that the future resembles the past. This idea was criticized by Hume and others as untenable leading to the famous problem of induction. It wasn't until the work of Karl Popper that this problem was solved, by demonstrating that induction is not the basis for science and that the development of scientific knowledge is instead based on the same principles as biological evolution. Today, machine learning is also taught as being rooted in induction from big data. Solomonoff induction implemented in an idealized Bayesian agent (Hutter's AIXI) is widely discussed and touted as a framework for understanding AI algorithms, even though real-world attempts to implement something like AIXI immediately encounter fatal problems. In this paper, we contrast frameworks based on induction with Donald T. Campbell's universal Darwinism. We show that most AI algorithms in use today can be understood as using an evolutionary trial and error process searching over a solution space. In this work we argue that a universal Darwinian framework provides a better foundation for understanding AI systems. Moreover, at a more meta level the process of development of all AI algorithms can be understood under the framework of universal Darwinism.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑