Beta-Convolutional Variational Autoencoder Streamlines Technosignature Searches in Breakthrough Listen Data

To the point

Using a beta-convolutional variational autoencoder, researchers analyze 480 hours of Green Bank Telescope data from 820 nearby Hipparcos stars to search for signs of alien technology in narrowband, Doppler-shifting radio signals; the semi-unsupervised approach greatly reduces false positives and cuts the candidate list by about 100x compared with earlier work, identifying eight new signals that haven’t been seen before but could not be reproduced on follow-up, illustrating that machine learning can accelerate SETI and related transient radio studies, with data and code publicly available.

Behold a Pale Horse
Behold a Pale Horse
Milton William Cooper
 The invisible college
The invisible college
Jacques Vallee
 Imminent: Inside the Pentagon’s Hunt for UFOs
Imminent: Inside the Pentagon’s Hunt for UFOs
Luis Elizondo
 American Cosmic: UFOs, Religion, Technology First Edition
American Cosmic: UFOs, Religion, Technology First Edition
D.W. Pasulka
Our recommendations from Amazon
A deep-learning search for technosignatures from 820 nearby stars - Nature Astronomy
nature.com

A deep-learning search for technosignatures from 820 nearby stars - Nature Astronomy

A state-of-the-art machine-learning method combs a 480-h-long dataset of 820 nearby stars from the SETI Breakthrough Listen project, reducing the number of interesting signals by two orders of magnitude. Further visual inspection identifies eight promising signals of interest from different stars that warrant further observations.