Title
Can machine learning identify interesting mathematics? An exploration using empirically observed laws.
Abstract
We explore the possibility of using machine learning to identify interesting mathematical structures by using certain quantities that serve as fingerprints. In particular, we extract features from integer sequences using two empirical laws: Benfordu0027s law and Tayloru0027s law and experiment with various classifiers to identify whether a sequence is nice, important, multiplicative, easy to compute or related to primes or palindromes.
Year
Venue
Field
2018
arXiv: Learning
Multiplicative function,Mathematical structure,Benford's law,Artificial intelligence,Law,Machine learning,Mathematics,Integer sequence
DocType
Volume
Citations 
Journal
abs/1805.07431
0
PageRank 
References 
Authors
0.34
1
1
Name
Order
Citations
PageRank
Chai Wah Wu133067.62