Artificial Intelligence , Now Aiding In the Search for , Extraterrestrial Intelligence.
According to a new paper published in the journal 'Nature Astronomy,' scientists are hoping to apply machine learning to the search for extraterrestrial life.
SETI, or the Search for Extraterrestrial Intelligence, was established in 1984 and has been scanning space for radio signals comprised of non-Earth based "technosignatures.".
VICE reports that a machine-learning algorithm was applied to telescope data collected in 2016.
.
After analyzing over 480 hours of data from 820 stars, the algorithm identified eight signals of interest that had previously gone undetected.
Peter Ma, the paper's first author, said that while artificial intelligence has been applied to SETI's data in the past, his team's approach is something new.
Previously people have inserted ML [machine learning] components into various pipelines to help with the search.
, Peter Ma, Undergraduate student at the University of Toronto, via VICE .
This work relies entirely on just the neural network without any traditional algorithms supporting it and produced results that traditional algorithms did not pick up, Peter Ma, Undergraduate student at the University of Toronto, via VICE .
According to Ma, his team's work is twice as fast as traditional algorithms and allows for an out-of-the-box approach to the search for alien intelligence.
Traditional algorithms operate on a given set of instructions designed by us… thus the algorithm will only ever discover what we tell it to find, Peter Ma, Undergraduate student at the University of Toronto, via VICE .
The issue is that the nature of an ET signal is not completely known… Hence our proposed approach is to just learn it, Peter Ma, Undergraduate student at the University of Toronto, via VICE
