ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1808.03884
19
14
v1v2v3 (latest)

A Basic Compositional Model for Spiking Neural Networks

12 August 2018
Nancy A. Lynch
Cameron Musco
    LRM
ArXiv (abs)PDFHTML
Abstract

We present a formal, mathematical foundation for modeling and reasoning about the behavior of synchronoussynchronoussynchronous, stochasticstochasticstochastic SpikingSpikingSpiking NeuralNeuralNeural NetworksNetworksNetworks (SNNs)(SNNs)(SNNs), which have been widely used in studies of neural computation. Our approach follows paradigms established in the field of concurrency theory. Our SNN model is based on directed graphs of neurons, classified as input, output, and internal neurons. We focus here on basic SNNs, in which a neuron's only state is a Boolean value indicating whether or not the neuron is currently firing. We also define the externalexternalexternal behaviorbehaviorbehavior of an SNN, in terms of probability distributions on its external firing patterns. We define two operators on SNNs: a compositioncompositioncomposition operatoroperatoroperator, which supports modeling of SNNs as combinations of smaller SNNs, and a hidinghidinghiding operatoroperatoroperator, which reclassifies some output behavior of an SNN as internal. We prove results showing how the external behavior of a network built using these operators is related to the external behavior of its component networks. Finally, we define the notion of a problemproblemproblem to be solved by an SNN, and show how the composition and hiding operators affect the problems that are solved by the networks. We illustrate our definitions with three examples: a Boolean circuit constructed from gates, an AttentionAttentionAttention network constructed from a WinnerWinnerWinner-TakeTakeTake-AllAllAll network and a FilterFilterFilter network, and a toy example involving combining two networks in a cyclic fashion.

View on arXiv
Comments on this paper