Accuracy and Efficiency in Fixed-Point Neural ODE Solvers

DOI10.1162/NECO_a_00772zbMath1472.92020OpenAlexW1896595291WikidataQ48591095 ScholiaQ48591095MaRDI QIDQ5380332

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)

Related Items (1)

Stochastic rounding and reduced-precision fixed-point arithmetic for solving neural ordinary differential equations

Uses Software

• Mathematica
• NEURON
• mctoolbox
• SpiNNaker

Cites Work

• Runge-Kutta type integration formulas including the evaluation of the second derivative. I
• Enhancing the implementation of mathematical formulas for fixed-point and floating-point arithmetics
• On explicit two-derivative Runge-Kutta methods
• Two-stage explicit Runge-Kutta type methods using derivatives
• On explicit one-step methods utilizing the second derivative
• Reliability of Spike Timing Is a General Property of Spiking Model Neurons
• On the Simulation of Nonlinear Bidimensional Spiking Neuron Models
• Importance of the Cutoff Value in the Quadratic Adaptive Integrate-and-Fire Model
• Solution Methods for a New Class of Simple Model Neurons
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Accuracy and Efficiency in Fixed-Point Neural ODE Solvers