Gmail Now Uses An Artificial Neural Network To Filter Spam

HardOCP News

[H] News
Joined
Dec 31, 1969
Messages
0
Have you noticed less spam in your Gmail account? More spam? Regular e-mail being classified as spam? This is probably the reason behind the changes.

Since the beginning, machine learning has helped make the Gmail spam filter more awesome. When you click the “Report spam” and “Not spam” buttons, you’re not only improving your Gmail experience right then and there, you’re also training Gmail’s filters to identify spam vs. wanted mail in the future. Now, we are bringing the same intelligence developed for Google Search and Google Now to make the spam filter smarter in a number of ways.
 
So I have an idea.

Let's all make a bunch of junk gmail accounts and select spam for legit emails and not spam for spam emails.
 
So I have an idea.

Let's all make a bunch of junk gmail accounts and select spam for legit emails and not spam for spam emails.

seems people on normal accounts do that already. i keep getting the same spam over and over again no matter how many times i click spam button.
 
Data_crying.jpg
 
Same here. I was surprised since it was really obvious spam, too.

They probably had to dial in the algorithms a bit.

A lot of this stuff you never learn until you deploy large scale. Long term I would expect this approach to be an improvement.
 
Zarathustra[H];1041723091 said:
They probably had to dial in the algorithms a bit.

A lot of this stuff you never learn until you deploy large scale. Long term I would expect this approach to be an improvement.

but I thought neural networks don't use predefined algorithms? not that I the slightest idea what actually going on at their back end
 
but I thought neural networks don't use predefined algorithms? not that I the slightest idea what actually going on at their back end

I guess (?) but they use a definition of 'fitness'... so which is google's? people's saying
'junk' /'not junk' in their email something like that?
Meh.
 
Back
Top