]]>
]]>
I'd love some feedback on a little something I have been working on for a year: fizz () is an experimental language and runtime environment for the exploration of cognitive architectures (#AI) combining Machine Learning (#ML) and Machine Reasoning (#MR) . While this mainly requires some beefy desktop/laptop, I have also built it for ARM so that I could run it on my Parallella board
Originally, I wanted to make use of the Epiphany cores, but I gross under-estimated how much memory I needed for each of the cores, so right now it's not using them
Still planning on using them at some point to offload some of the computation. Meanwhile, since it's only running on the ARM the performances are far from stellar.Anyway, I thought I'll share that project with the community.
Cheers,
Statistics: Posted by CocoaGeek — Tue Dec 05, 2017 4:45 am
]]>
]]>
]]>
It will not be very efficient given that it is single threaded and it is limited to one hidden layer but it will give you an idea of what I am heading for at the moment.
Statistics: Posted by nickoppen — Sat Feb 07, 2015 5:13 am
]]>
I'm writing one at the moment which I'm open sourcing. Early days as yet, I've just got a simple feed forward kernel going (I'm writing in OpenCL).
I'm really keen to get hold of a big data set to do some training and test out performance and scalability.
I've written some blog posts on my ideas about getting the best out of the Parallella which you can read here: and my neural network repo is here: .
I'll have a look at your repo and see what tweaks you are using. What I have written to date has no fancy stuff at all so I've got plenty of scope to add them in.
This is my "after the kids are in bed" project to things are a bit slow, but I'd be happy to work with you on it.
nick
Statistics: Posted by nickoppen — Fri Feb 06, 2015 10:19 pm
]]>
Please see the for previous discussion concerning neural networks.
Regards,
Andrew
Statistics: Posted by 9600 — Thu Feb 05, 2015 9:13 am
]]>
I am currently using a neural network program called emergent from the University of Colorado, running it on Linux. the application uses a back propagation (Bp) model in my case to find correlations between energy consumption and solar generation for buildings and local environmental conditions and time-series data. The current version of emergent is great! it runs on Windows, OSX, and with Linux x86 and x86_64 on Ubuntu and Debian and uses I believe up to 4 cores conncurrently, and possibly can run on other architectures too. Fully open-source. Anyway I do like emergent a lot - but am interested in using Parallella hardware for this fairly compute intensive component of our energy management software platform which is called SolarNetwork, which is also 100% open-source (https://github.com/SolarNetwork), and uses the Pi and other low-cost boards for data collection.
My questions are:
-What would it take for emergent to support Parallela/Epiphany hardware?
-Are there any Parallella developers interested in looking at that project?
-Are there any existing ANN packages/applications that are 100% open-source and run on Parallella now?
Thanks, John
Statistics: Posted by jwgorman — Wed Feb 04, 2015 10:16 pm
]]>
Statistics: Posted by Gerald — Thu Aug 14, 2014 1:42 pm
]]>
Nice work with the pi!
Unfortunately there hasn't been an official BLAS library completed yet.
Take a look at the following example showing how it could be scaled out.
https://github.com/adapteva/epiphany-ex ... /matmul-16
What size matrices are you working with?
Andreas
Statistics: Posted by aolofsson — Mon Aug 11, 2014 5:37 pm
]]>
]]>
]]>
The training part has been my big "how is that going to happen" issue. It's a highly asymetric process.
Statistics: Posted by Cyberman.ff — Sat Jul 19, 2014 8:09 pm
]]>
Look forward to your thoughts.
Andreas
Statistics: Posted by aolofsson — Mon Jul 14, 2014 8:51 am
]]>