IMNN: Information Maximizing Neural Networks

Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 1916
Joined: Thu May 08, 2014 5:37 am

IMNN: Information Maximizing Neural Networks

Post by Ada Coda » Sun Apr 29, 2018 12:25 am

IMNN: Information Maximizing Neural Networks

Abstract: This software trains artificial neural networks to find non-linear functionals of data that maximize Fisher information: information maximizing neural networks (IMNNs). As compressing large data sets vastly simplifies both frequentist and Bayesian inference, important information may be inadvertently missed. Likelihood-free inference based on automatically derived IMNN summaries produces summaries that are good approximations to sufficient statistics. IMNNs are robustly capable of automatically finding optimal, non-linear summaries of the data even in cases where linear compression fails: inferring the variance of Gaussian signal in the presence of noise, inferring cosmological parameters from mock simulations of the Lyman-α forest in quasar spectra, and inferring frequency-domain parameters from LISA-like detections of gravitational waveforms. In this final case, the IMNN summary outperforms linear data compression by avoiding the introduction of spurious likelihood maxima.

Credit: Charnock, Tom; Lavaux, Guilhem; Wandelt, Benjamin D.

Site: https://doi.org/10.5281/zenodo.1119069
https://ui.adsabs.harvard.edu/abs/2018PhRvD..97h3004C

Bibcode: 2018ascl.soft04014C

Preferred citation method: https://ui.adsabs.harvard.edu/abs/2018PhRvD..97h3004C

ID: ascl:1804.014
Last edited by Ada Coda on Thu Jul 18, 2019 9:38 pm, edited 1 time in total.
Reason: Updated code entry.

Post Reply