Boffins deploy machine learning in search for intelligent ET

Scientists have developed a machine learning method they think could help filter out interference and more efficiently spot unusual radio signals from space, contributing to the ongoing search for extra-terrestrial intelligence. Search for extraterrestrial intelligence (SETI) programmes have used radio telescopes for decades …

[Pascal Monett]

"a viable analysis tool, out-scaling the world’s largest super-computers"

And that was back in the naughties, when the CPU was the only thing doing calculations.

To think of what could be achieved in analysis with today's GPUs and their massively parallel threads . . .

The SETI screensaver would just be a blur of colors.

I'm getting goosebumps just thinking about it.

[Version 1.0]

Re: "a viable analysis tool, out-scaling the world’s largest super-computers"

Look at the history of the Universe since the Big Bang and the chance of intelligent ET existing is probably low. Our sun is about 4.6 billion years old and we're thinking that, based on observations of other stars, it will reach the end of its life in about another 10 billion years. This seems to be a common Universe event so the chances of seeing ET is low because this is probably happening everywhere. We're only here because sixty-six million years ago, dinosaurs had a bad day, if that had not happened then we probably would not exist to have this conversation.

[Harry Kiri]

Unfortunately I find this unconvincing

Machine learning needs realistic training data to perform a classification task, which this is - is the data presented a 'technosignature' or not. Ideally you'd like a classifier that says 'I've seen something anomalous or different to what I've seen' but that's not how classifiers work, you do need representative data for each of the classes. (Humans are really good at noticing when things are odd without representative data, ML classifiers are not). There is no representative data for a technosignature so its a complete guess if one makes it artificially. This guess is driven into the classifier.

So interesting work and a great idea for a 3rd year undergrad project where it's really more about the project than the discovery, but this isn't serious analysis of 'its aliens'!

[Anonymous Coward]

All it would take

Just one verified extraterrestrial message.

And the religious apologists would go into hyperdrive.

[Fruit and Nutcase]

Re: All it would take

And when ET comes and says "take me to your leader", they won't be able to decide who, and start fighting with each other. Oh, wait

[Bebu]

Re: All it would take

"take me to your leader" - myself I would introduce the visitors to the Dali Lama.

Not a bad chap and would send Xi and co. in the middle kingdom incandescent.

Hopefully not visitors of "V" fame - I would not want the poor fellow eaten.

I would have thought the ML would need a training set to be able to detect intelligent. AFAIK there isn't any earthside

With a bit of luck they will only turn up a whole new collection of pulsars.

[amanfromMars 1]

Re: All it would take

And when ET comes and says "take me to your leader", they won't be able to decide who, and start fighting with each other. Oh, wait ..... Fruit and Nutcase

A current present running situation, Fruit and Nutcase, which A.N.Others before you have Registered and agreed does neither require nor benefit from conflicted inhuman input because of the negative resultant consequences of its output ........ https://forums.theregister.com/forum/all/2023/01/06/ai_conference_nyc_ban/#c_4596479

[xyz]

The bloke with the hair...

From Ancient Aliens still gives me the willies... I'm sure he's not from around here... and when I say around here, I mean umpteen light years from around here.

Anyhoo... I'm sure the researchers involved will be having their collars felt by the MiB pronto.

[Adair]

Potentially good odds ...

that currently we are the only game in town, at least in our galaxy;

or, that anyone advanced enough to be swanning about the galaxy, or even their own system, long ago stopped broadcasting their presence in the clear in favour of far more effiicient opaque/tight communications systems.

Not suggesting it's not worth looking, but I wouldn't be holding my breath for a positive result.

As for the 'religious meltdown' snark, that betrays a certain level of immaturity and/or ignorance. I think you will find that most 'religions' of any substance would actually cope fine with the 'aliens are out there' news. OTOH, there are people all over whose world will collapse in an explosion of 'rigid literalism' being shattered by reality.

[Plest]

Before anyone else says it, given the state of some of the nonsense we put up with these days from our leaders and other numpties trying to ruin our day, I think we should start trying to locate intelligent life on this planet before we go looking elsewhere, intelligence seems to be in very short supply these days!

[ChaosFreak]

Fermi Patadox

It's cool they've developed some tech to clean up signals, which could be useful elsewhere, but searching for extraterrestrial intelligence is a complete waste of time and money.

As Fermi proved long ago, if we were going to make contact with extraterrestrial intelligence, we should already have done so many times over.

It's just a numbers game. Even at 10% of the speed of light, an intelligent species could colonize the entire galaxy in less than a million years. Given that the galaxy is over 13 billion years old, and it only took just over 4 billion years for intelligence with the capability of space travel to arise on Earth, If the probability that intelligent life arises on a planet other than Earth is anything other than zero, it should have already happened over and over and over again in the history of the galaxy. As the SETI people like to say, with 100 billion stars in the galaxy, and 14 billion years to play out, any non-zero probability of the existence of extraterrestrial life means it is definitely out there. What Fermi says is, sure, in that case it should be EVERYWHERE, so where is everybody?

The fact that we see no evidence of this means that for some reason intelligent life does not spread throughout the galaxy in a way that is detectable by other intelligent life. It doesn't mean it's not there, it just means we will never detect it, because if we were going to, we would have done so by now, given the age and number of stars in the galaxy.

And before anyone starts posting "objections", Note that virtually every objection to the Fermi paradox only proves the paradox when you think about it.

Maybe all intelligent life destroys itself in a great firewall? You've just proved the paradox.

Maybe all intelligent life develops to a point where they communicate by means that are undetectable by us? You've just proved the paradox.

Maybe all intelligent life decides that colonizing the galaxy is not a worthwhile pursuit? You've just proved the paradox.

Maybe intelligent life is so exceedingly rare, that even with 100 billion stars in the galaxy humanity is the only intelligent life? You've just proved the paradox.

Sad, since I'd love to meet ET, but unfortunately it's the reality of the numbers.

(By the way, I am aware that there is some doubt as to the provenance of the Fermi paradox.)

[ChaosFreak]

Re: Fermi Patadox

LOL, Patadox

Looks like I may not be a terrestrial intelligence

[lamp]

Space is very, very, very big ...

... and they're have difficulty in finding us