3 papers
cs.AI2026
Compression is all you need: Modeling Mathematics
Vitaly Aksenov, Eve Bodnia, Michael H. Freedman +1
Human mathematics (HM), the mathematics humans discover and value, is a vanishingly small subset of formal mathematics (FM), the totality of all valid deductions. We argue that HM…
cs.LG2025
Spontaneous Kolmogorov-Arnold Geometry in Shallow MLPs
Michael H. Freedman, Michael Mulligan
The Kolmogorov-Arnold (KA) representation theorem constructs universal, but highly non-smooth inner functions (the first layer map) in a single (non-linear) hidden layer neural net…
math.NA2024
The Proof of Kolmogorov-Arnold May Illuminate Neural Network Learning
Michael H. Freedman
Kolmogorov and Arnold, in answering Hilbert's 13th problem (in the context of continuous functions), laid the foundations for the modern theory of Neural Networks (NNs). Their proo…