On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel wrote:
> maybe we should drop the name Mahout altogether.
I have been told that there is a cool secondary interpretation of Mahout as
well.
I think that the Hebrew word is pronounced roughly like Mahout.
מַהוּת
The cool
Hi folks,
I have been following Mahout for a long time. I used it in some of my
projects.
Honey Badget... yes I think it is cool and funny. But I think it is not
able to represent the Mahout. Mahout is about learning, math and abstract
things.
What does describe Mahout better? For me,
"Doing
Hi , I am a newcomer to the project, and I think the current website
definitely could use a re-build. One of the things I think that enables
quick adoption of any new project are the quick start tutorials. In
particular I like the way the Apache zeppelin site is structured. There is
a lot of
To date we have referred to the GPU/CPU/CUDA as 'pluggable native-solvers'.
'plugable backends' are the Spark - Flink -H20- whatever.
With the advent of both, I could see the confusion and we may want to
rethink the naming as part of of this too.
Trevor Grant
Data Scientist
I don't think the backends we have now off the shelf are particularly
exciting, but the fact you CAN plug different ones back in is the value
prop (and a big one that we need to 'sell' more). The difference is subtle
but since this is the marketing thread also worth bringing up. Basically to
your
On Fri, Mar 24, 2017 at 8:27 AM, Pat Ferrel wrote:
> The multiple backend support is such a waste of time IMO. The DSL and GPU
> support is super important and should be made even more distributed. The
> current (as I understand it) single threaded GPU per VM is only the
The multiple backend support is such a waste of time IMO. The DSL and GPU
support is super important and should be made even more distributed. The
current (as I understand it) single threaded GPU per VM is only the first step
in what will make Mahout important for a long time to come.
Think of