Wolves Howl In Different 'Dialects,' Machine Learning Finds (vice.com)

derekmead writes: Differentiating wolf howls with human ears can prove tricky, so researchers have turned to computer algorithms to suss out if different wolf species howl differently. They think that understanding wolf howls could help improve wolf conservation and management programs. In a study published in the journal Behavioural Processes, a group of international researchers describe using machine learning for the first time to analyze 2,000 wolf howls gathered from both wild and domesticated wolves and their subspecies from around the world.

Comments

Re: Suss out?

[WarJolt]

Dude, don't lump me in with him. I think most of us Americans know what suss out means.

it's not what is said

[turkeydance]

it's HOWL it's said

Re: Suss out?

[PPH]

And if we don't, we'll suss it out eventually.

more specifically, a clustering algorithm

[Trepidity]

I guess anything but trivial clustering algorithms are "machine learning", but rather than "using machine learning" it'd be more straightforward to describe them as having "applied a clustering algorithm" to see if calls can be grouped into, well, different clusters. That is an idea that's been floating around biology now and then, with a lot of work on clustering bird calls especially.

Oblig. Far Side

[Okian Warrior]

Gary Larson predicted this.

Re:If only

[AmiMoJo]

We have known for a while that other animals have regional accents. Dogs can only make a small number of different vocalizations, but cats can make over 100. Sure enough, cats have regional accents.