Let's Make Robots!

BeagleBone: Neural Network Control

General Adaptive Learning

BeagleBone: Neural Network Control http://nn-os.org/ provides a new computing environment for Neural Network Control applications of all sorts. Essentially the environment is comprised of two REAL-TIME components: 1. Neural Network adaptive learning, currently back-propagation 2. Petri Nets with BSD sockets to orchestrate asynchronous multi-tasking and IO across the networks For examples see: http://nn-os.org/nnconductor/ http://nn-os.org/petri-net-nnnet2/ http://nn-os.org/petri-net-nnnet2-2/ The software is optimized using the vectorization flags of the gcc compiler on BeagleBone board. Therefore 1000 training for 10x64x10 Neural Network is accomplished in 1 second or less. We are looking for novel robotic and UAV applications to better hone and focus our code. The enlightened and creative talents are encouraged to respond for possible joint projects. The code is provided under the Apache 2.0 dual license. Dara

Comment viewing options

Select your preferred way to display the comments and click "Save settings" to activate your changes.

I just started playing with a beaglebone and it is a pretty awesome little system for the price.  Having linux makes it great in a lot of ways.  I'll through up a post when I do something worthwhile with it.

Hello 

If you build a roboto or UAV, I will code the NN and all the comm software for you, I need to build my expertise in NN with actual robotos and UAVs

 

Thanx

 

Dara

If someone will drop that into a robot and show details of how it is done, I will very much consider getting s BeagleBone.

http://beagleboard.org/project/robot+cleaner/ there are more of them at http://beagleboard.org/project 

 

They also support android.

 

 

COOL!!!!!

I will code the neural networks and petri nets for you + now beaglebone has WIFI radios for their boards, you can get the Petri Nets to communicate with other devices, including another one of your robots ... 

neural nets!!!! nice!

I've been pleading with LMRians for anything on the Beagles.  Thanks!  Any experience with openCV/openNI on the platform?

Sure thing, let me know what your ideas are, I will definitely do machine vision for Beaglbone, probably next couple of weeks

 

I might do SVM: http://en.wikipedia.org/wiki/Support_vector_machine 

... I do not understand a thing about them or what they do.

Maybe you can do a tutorial here on LMR so we can understand?