Graph Rules for Recurrent Neural Network Dynamics

2023/03/09 by Carina Curto, Katherine Morrison, Katherine M. Morrison · 4 citations
Computer Science · #Neural Networks and Applications

paper · pdf · doi:10.1090/noti2661

Abstract

We describe a class of inhibition-dominated neural networks corresponding to directed graphs, and introduce some of the theory that has been developed to study them. The heart of the theory is a set of parameter-independent graph rules that enables us to directly predict features of the dynamics from combinatorial properties of the graph.

Cited by

• A six-neuron counterexample to the target-free clique conjecture
• Strata of Ecological Coexistence via Grassmannians
• On graphical domination for threshold-linear networks with recurrent excitation and global inhibition
• Detecting Invariant Manifolds in ReLU-Based RNNs

Related

• Graph rules for recurrent neural network dynamics: extended version
• Predicting neural network dynamics via graphical analysis
• Nerve theorems for fixed points of neural networks
• Sequence generation in inhibition-dominated neural networks
• Diverse mean-field dynamics of clustered, inhibition-stabilized Hawkes networks via combinatorial threshold-linear networks