Nearest Neighbor Representations of Neural Circuits

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kilic, Kordag Mehmet, Sima, Jin, Bruck, Jehoshua
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911872245039104
author Kilic, Kordag Mehmet
Sima, Jin
Bruck, Jehoshua
author_facet Kilic, Kordag Mehmet
Sima, Jin
Bruck, Jehoshua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08751
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nearest Neighbor Representations of Neural Circuits
Kilic, Kordag Mehmet
Sima, Jin
Bruck, Jehoshua
Computational Complexity
Discrete Mathematics
Machine Learning
Neural and Evolutionary Computing
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.
title Nearest Neighbor Representations of Neural Circuits
topic Computational Complexity
Discrete Mathematics
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2402.08751