TOWARD A MATHEMATICAL THEORY OF INDUCTIVE INFERENCE
TOWARD A MATHEMATICAL THEORY OF INDUCTIVE INFERENCE
复制标题
DOI：
10.1016/s0019-9958(75)90261-2
复制
发表时间：
1975-01-01
影响因子：
--
通讯作者：
BLUM, M
中科院分区：
文献类型：
--
作者：
BLUM, L;BLUM, M
智力测验有时需要外推一个有效的序列（如1661，2552，3663，...）这是由一些容易识别的算法产生的。在本文中，我们调查的理论能力和计算机的局限性，以推断这样的序列。我们设计的图灵机在原理上非常强大，并为机器的能力设定了上限，我们希望对几个过程进行建模。一种是有效序列的外推，其中序列的前几个元素以某种方式用于生成下一个元素。另一个是寻找科学规律。想想看，一个物理学家在寻找一条定律来解释一个不断增长的身体
Intelligence tests occasionally require the extrapolation of an effective sequence (eg 1661, 2552, 3663,...) that is produced by some easily discernible algorithm. In this paper, we investigate the theoretical capabilities and limitations of a computer to infer such sequences. We design Turing machines that in principle are extremely powerful for this purpose and place upper bounds on the capabilities of machines that would do better.There are several processes we wish to model. One is the extrapolation of effective sequences, wherein the first few elements of a sequence are used somehow for generating the next element. Another is the search for scientific law. Consider the physicist who looks for a law to explain a growing body