Speculation on graph computation architectures and computing via synchronization

TL;DR

This paper explores speculative ideas about future graph computation architectures and neural networks that utilize arc-based synchronization, aiming to inspire further research in these emerging areas.

Contribution

It introduces novel concepts of graph-based computation models and arc-based neural networks, emphasizing the potential of synchronization mechanisms.

Findings

Proposes the idea of computation with graphs as a future research area

Introduces arc-based neural networks that store information via arc modifications

Suggests synchronization as a key element in neural network architectures

Abstract

A speculative overview of a future topic of research. The paper is a collection of ideas concerning two related areas: 1) Graph computation machines ("computing with graphs"). This is the class of models of computation in which the state of the computation is represented as a graph or network. 2) Arc-based neural networks, which store information not as activation in the nodes, but rather by adding and deleting arcs. Sometimes the arcs may be interpreted as synchronization. Warnings to readers: this is not the sort of thing that one might submit to a journal or conference. No proofs are presented. The presentation is informal, and written at an introductory level. You'll probably want to wait for a more concise presentation.