Fixed Points of Competitive Threshold-Linear Networks

DOI10.1162/NECO_A_01151MaRDI QIDQ3379579zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Katherine Morrison, Carina Curto, Jesse Geneson

Publication date 27 September 2021

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1804.00794

zbMATH Keywords

combinatorial threshold-linear neural networksperceptron-like neurons

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: Threshold-linear networks (TLNs) are models of neural networks that consist of simple, perceptron-like neurons and exhibit nonlinear dynamics that are determined by the network's connectivity. The fixed points of a TLN, including both stable and unstable equilibria, play a critical role in shaping its emergent dynamics. In this work, we provide two novel characterizations for the set of fixed points of a competitive TLN: the first is in terms of a simple sign condition, while the second relies on the concept of domination. We apply these results to a special family of TLNs, called combinatorial threshold-linear networks (CTLNs), whose connectivity matrices are defined from directed graphs. This leads us to prove a series of graph rules that enable one to determine fixed points of a CTLN by analyzing the underlying graph. Additionally, we study larger networks composed of smaller "building block" subnetworks, and prove several theorems relating the fixed points of the full network to those of its components. Our results provide the foundation for a kind of "graphical calculus" to infer features of the dynamics from a network's connectivity.

Recommendations

• Stability and bifurcations of equilibria in networks with piecewise linear interactions
• Rigorous results on the threshold network model
• Equilibria and their stability in networks with steep sigmoidal nonlinearities
• Synchronicity in non-smooth competitive networks with threshold nonlinearities
• Threshold-based network structural dynamics
• Threshold-based network structural dynamics
• scientific article; zbMATH DE number 1254383
• Stochastic networks with multiple stable points
• Universality of competitive networks in complex networks

Cites work

• Encoding binary neural codes in networks of threshold-linear neurons
• Flexible memory networks
• Neural networks and physical systems with emergent collective computational abilities
• Pattern completion in symmetric threshold-linear networks
• Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks
• Predicting neural network dynamics via graphical analysis
• Selectively Grouping Neurons in Recurrent Networks of Lateral Inhibition

Cited in

(12)

• Stable fixed points of combinatorial threshold-linear networks
• Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks
• Topological model of neural information networks
• Predicting neural network dynamics via graphical analysis
• Sequential Attractors in Combinatorial Threshold-Linear Networks
• Random weights of DNNs and emergence of fixed points
• Diversity of emergent dynamics in competitive threshold-linear networks
• State-dependent effective interactions in oscillator networks through coupling functions with dead zones
• Condorcet winner configurations of linear networks
• Pattern completion in symmetric threshold-linear networks
• Periodic solutions in threshold-linear networks and their entrainment
• Nerve theorems for fixed points of neural networks

This page was built for publication: Fixed Points of Competitive Threshold-Linear Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3379579)