Accuracy and efficiency in fixed-point neural ODE solvers

DOI10.1162/NECO_A_00772zbMATH Open1472.92020DBLPjournals/neco/HopkinsF15OpenAlexW1896595291WikidataQ48591095 ScholiaQ48591095MaRDI QIDQ5380332FDOQ5380332

Authors Michael Hopkins, Steve B. Furber

Publication date 4 June 2019

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_00772

Mathematics Subject Classification ID

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

Recommendations

• Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equations
• Accuracy evaluation of numerical methods used in state-of-the-art simulators for spiking neural networks
• Exact digital simulation of time-invariant linear systems with applications to neuronal modeling
• Efficient Implicit Runge-Kutta Methods for Fast-Responding Ligand-Gated Neuroreceptor Kinetic Models
• Solution Methods for a New Class of Simple Model Neurons

Cites work

• scientific article; zbMATH DE number 52120 (Why is no real title available?)
• scientific article; zbMATH DE number 3543543 (Why is no real title available?)
• scientific article; zbMATH DE number 2006091 (Why is no real title available?)
• scientific article; zbMATH DE number 846277 (Why is no real title available?)
• scientific article; zbMATH DE number 274379 (Why is no real title available?)
• scientific article; zbMATH DE number 3251027 (Why is no real title available?)
• scientific article; zbMATH DE number 3306964 (Why is no real title available?)
• scientific article; zbMATH DE number 3408831 (Why is no real title available?)
• scientific article; zbMATH DE number 3182507 (Why is no real title available?)
• scientific article; zbMATH DE number 3064499 (Why is no real title available?)
• Enhancing the implementation of mathematical formulas for fixed-point and floating-point arithmetics
• Importance of the Cutoff Value in the Quadratic Adaptive Integrate-and-Fire Model
• Numerical initial value problems in ordinary differential equations.
• On explicit one-step methods utilizing the second derivative
• On explicit two-derivative Runge-Kutta methods
• On the simulation of nonlinear bidimensional spiking neuron models
• Reliability of Spike Timing Is a General Property of Spiking Model Neurons
• Runge-Kutta type integration formulas including the evaluation of the second derivative. I
• Solution Methods for a New Class of Simple Model Neurons
• Two-stage explicit Runge-Kutta type methods using derivatives

Cited in

(3)

• Accuracy evaluation of numerical methods used in state-of-the-art simulators for spiking neural networks
• Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equations
• Collocation based training of neural ordinary differential equations

Describes a project that uses

Uses Software

• Mathematica
• NEURON
• mctoolbox
• SpiNNaker

This page was built for publication: Accuracy and efficiency in fixed-point neural ODE solvers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380332)