A basic compositional model for spiking neural networks

DOI10.1007/978-3-031-15629-8_22MaRDI QIDQ6108904zbMATH OpenFDO

Authors Nancy Lynch, Cameron Musco

Publication date 26 July 2023

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1808.03884

zbMATH Keywords

composition of networkscompositionalityspiking neural networks

Mathematics Subject Classification ID

Networks and circuits as models of computation; circuit complexity (68Q06) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: We present a formal, mathematical foundation for modeling and reasoning about the behavior of $synchronous$, $stochastic$ $Spiking$ $Neural$ $Networks$ $(SNNs)$, 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 $external$ $behavior$ of an SNN, in terms of probability distributions on its external firing patterns. We define two operators on SNNs: a $composition$ $operator$, which supports modeling of SNNs as combinations of smaller SNNs, and a $hiding$ $operator$, 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 $problem$ 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 $Attention$ network constructed from a $Winner$-$Take$-$All$ network and a $Filter$ network, and a toy example involving combining two networks in a cyclic fashion.

Recommendations

• Spiking neural networks modelled as timed automata: with parameter learning
• On the Algorithmic Power of Spiking Neural Networks
• Computational Properties of Networks of Synchronous Groups of Spiking Neurons
• Compositional semantics of spiking neural P systems
• Modeling spiking neural networks

Cites work

• A logical calculus of the ideas immanent in nervous activity
• A neural algorithm for a fundamental computing problem
• Computational tradeoffs in biological neural networks: self-stabilizing winner-take-all networks
• Counting to Ten with Two Fingers: Compressed Counting with Spiking Neurons.
• Forward and backward simulations. I. Untimed Systems
• Forward and backward simulations. II: Timing-based systems
• Front Matter, Table of Contents, Preface, Conference Organization
• Fundamentals of computational neuroscience
• scientific article; zbMATH DE number 996442 (Why is no real title available?)
• scientific article; zbMATH DE number 4110131 (Why is no real title available?)
• scientific article; zbMATH DE number 794262 (Why is no real title available?)
• scientific article; zbMATH DE number 826255 (Why is no real title available?)
• Hybrid I/O automata.
• Learning hierarchically-structured concepts
• Neuro-RAM unit with applications to similarity testing and compression in spiking neural networks
• Observing branching structure through probabilistic contexts
• On the complexity of learning for spiking neurons with temporal coding.
• Random projection in the brain and computation with assemblies of neurons
• Random Sketching, Clustering, and Short-Term Memory in Spiking Neural Networks.
• Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits
• The Theory of Timed I/O Automata
• What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?

Cited in

(3)

• On the Algorithmic Power of Spiking Neural Networks
• Spiking neural networks modelled as timed automata: with parameter learning
• Learning hierarchically-structured concepts. II: Overlapping concepts, and networks with feedback

This page was built for publication: A basic compositional model for spiking neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6108904)