Nearest Neighbor Representations of Neural Circuits

Autor:	Kilic, Kordag Mehmet, Sima, Jin, Bruck, Jehoshua
Rok vydání:	2024
Předmět:	Computer Science - Computational Complexity Computer Science - Discrete Mathematics Computer Science - Machine Learning Computer Science - Neural and Evolutionary Computing
Druh dokumentu:	Working Paper
Popis:	Neural networks successfully capture the computational power of the human brain for many tasks. Similarly inspired by the brain architecture, Nearest Neighbor (NN) representations is a novel approach of computation. We establish a firmer correspondence between NN representations and neural networks. Although it was known how to represent a single neuron using NN representations, there were no results even for small depth neural networks. Specifically, for depth-2 threshold circuits, we provide explicit constructions for their NN representation with an explicit bound on the number of bits to represent it. Example functions include NN representations of convex polytopes (AND of threshold gates), IP2, OR of threshold gates, and linear or exact decision lists. Comment: This paper is accepted to ISIT 2024. 2nd version has revisions for better clarity, more citations, and more explanation in the proofs. No results are changed
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.08751 Zobrazit plný text záznamu View this record from Arxiv