Studying number theory with deep learning: a case study with the Möbius and squarefree indicator functions
Building on work of Charton, we train small transformer models to calculate the M\"obius function $\mu(n)$ and the squarefree indicator function $\mu^2(n)$. The models attain nontrivial predictive power. We then iteratively train additional models to understand how the model functions, ultimately finding a theoretical explanation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Weighted Möbius Score: A Unified Framework for Feature Attribution
Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between mu…
Sentiment AnalysisComputational Aspects of the Mobius Transform
In this paper we associate with every (directed) graph G a transformation called the Mobius transformation of the graph G. The Mobius transformation of the graph (O) is of major significance for Dempster-Shafer theory of…
Imbalance Prime Sieving: Every Prime Gap Is a Result of a Möbius Imbalance Obstruction
We introduce a novel sieve for prime numbers based on detecting topological obstructions in a Möbius-transformed rational metric space. Unlike traditional sieves which rely on divisibility, our method identifies primes a…
Learning to Understand: Identifying Interactions via the Möbius Transform
One of the key challenges in machine learning is to find interpretable representations of learned functions. The M\"obius transform is essential for this purpose, as its coefficients correspond to unique importance score…
Learning TheoryFree resolutions of function classes via order complexes
Function classes are collections of Boolean functions on a finite set, which are fundamental objects of study in theoretical computer science. We study algebraic properties of ideals associated to function classes previo…
Learning Theory