A Theory of Sequence Indexing and Working Memory in Recurrent Neural Networks

DOI10.1162/neco_a_01084zbMath1472.68055arXiv1803.00412OpenAlexW2963650979WikidataQ52590061 ScholiaQ52590061MaRDI QIDQ5157184

E. Paxon Frady, Friedrich T. Sommer, Denis Kleyko

Publication date: 12 October 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.00412

Mathematics Subject Classification ID

Networks and circuits as models of computation; circuit complexity (68Q06)

Related Items (2)

Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures ⋮ A Theoretical Perspective on Hyperdimensional Computing

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• Analytic study of the memory storage capacity of a neural network
• Memory in linear recurrent neural networks in continuous time
• Asymptotics for some fundamental \(q\)-functions
• Binding and Normalization of Binary Sparse Distributed Representations by Context-Dependent Thinning
• Noise Tolerance of Attractor and Feedforward Memory Models
• A table of normal integrals
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Neural networks and physical systems with emergent collective computational abilities.
• Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
• Randomly Connected Networks Have Short Temporal Memory
• Representing Objects, Relations, and Sequences
• Short-Term Memory Capacity in Networks via the Restricted Isometry Property
• Probability of error, equivocation, and the Chernoff bound
• On Information and Sufficiency
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations

This page was built for publication: A Theory of Sequence Indexing and Working Memory in Recurrent Neural Networks