> This sounds like that old conversation coming back to life. Stop using
> GroundedPredicateNodes. Start using Values. That is what they are there
> for. That is what they were created for. FloatValue was created last
> summer, specifically for the neural-net/tensorflow project.
>
I mean, at the time, I was pretty happy with it, I thought it was really
pretty slick. After that pull req, you could do things like ((3 *
vector-neuron A + 42 * vector-neuron B) <= vector-neuron C) all in atomese,
all with vectors, and it would just call the `update()` method
automatically to get the latest vectors from your tensorflow network. The
wiki page here gives examples:
https://wiki.opencog.org/w/ValueOfLink
Like I say, I thought it was pretty slick; I'm disappointed you didn't use
that API.
-- Linas
--
cassette tapes - analog TV - film cameras - you
--
You received this message because you are subscribed to the Google Groups
"opencog" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/opencog.
To view this discussion on the web visit
https://groups.google.com/d/msgid/opencog/CAHrUA358GPDSCCU6yNmjZdMmPShF53jCYm2EE9icrvqAxAukbw%40mail.gmail.com.
For more options, visit https://groups.google.com/d/optout.
