Pattern completion in symmetric threshold-linear networks
From MaRDI portal
Abstract: Threshold-linear networks are a common class of firing rate models that describe recurrent interactions among neurons. Unlike their linear counterparts, these networks generically possess multiple stable fixed points (steady states), making them viable candidates for memory encoding and retrieval. In this work, we characterize stable fixed points of general threshold-linear networks with constant external drive, and discover constraints on the co-existence of fixed points involving different subsets of active neurons. In the case of symmetric networks, we prove the following antichain property: if a set of neurons is the support of a stable fixed point, then no proper subset or superset of can support a stable fixed point. Symmetric threshold-linear networks thus appear to be well suited for pattern completion, since the dynamics are guaranteed not to get "stuck" in a subset or superset of a stored pattern. We also show that for any graph G, we can construct a network whose stable fixed points correspond precisely to the maximal cliques of G. As an application, we design network decoders for place field codes, and demonstrate their efficacy for error correction and pattern completion. The proofs of our main results build on the theory of permitted sets in threshold-linear networks, including recently-developed connections to classical distance geometry.
Recommendations
Cites work
- Combinatorial neural codes from a mathematical coding theory perspective
- Encoding binary neural codes in networks of threshold-linear neurons
- Flexible memory networks
- Geometry. I, II. Transl. from the French by M. Cole and S. Levy
- scientific article; zbMATH DE number 3974960 (Why is no real title available?)
- scientific article; zbMATH DE number 1164156 (Why is no real title available?)
- Matrix Analysis
- Neural networks and physical systems with emergent collective computational abilities
- Neurons with graded response have collective computational properties like those of two-state neurons
- Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks
- Selectively Grouping Neurons in Recurrent Networks of Lateral Inhibition
Cited in
(13)- Nerve theorems for fixed points of neural networks
- Heteroclinic cycles in a competitive network
- Fixed Points of Competitive Threshold-Linear Networks
- Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks
- Synchronicity in non-smooth competitive networks with threshold nonlinearities
- Sequential Attractors in Combinatorial Threshold-Linear Networks
- Periodic solutions in threshold-linear networks and their entrainment
- Periodic orbits and chaos in nonsmooth delay differential equations
- Encoding binary neural codes in networks of threshold-linear neurons
- Stable fixed points of combinatorial threshold-linear networks
- Diversity of emergent dynamics in competitive threshold-linear networks
- Oscillatory networks: insights from piecewise-linear modeling
- The combinatorial code and the graph rules of dale networks
This page was built for publication: Pattern completion in symmetric threshold-linear networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380605)
