NELGCORAJul 29, 2023

Discrete neural nets and polymorphic learning

arXiv:2308.00677v2h-index: 1
Originality Synthesis-oriented
AI Analysis

This work provides a theoretical bridge between neural networks and algebra, potentially offering new insights for discrete learning problems, but it appears incremental as it adapts existing concepts to a discrete setting.

The paper tackles the problem of unifying universal approximation theorems from neural networks and universal algebra by introducing a discrete analogue of neural nets and a learning algorithm based on polymorphisms of relational structures, demonstrating its application to a classical learning task.

Theorems from universal algebra such as that of Murskiĭ from the 1970s have a striking similarity to universal approximation results for neural nets along the lines of Cybenko's from the 1980s. We consider here a discrete analogue of the classical notion of a neural net which places these results in a unified setting. We introduce a learning algorithm based on polymorphisms of relational structures and show how to use it for a classical learning task.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes