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.

http://nn-os.org/nnconductor/ this gives you a pretty good idea about what NN does, there are not Petri Nets in this application.

 

If you need more explanations let me know but the printouts are fairly clear and added some sound files for more clarity. 

 

Also on the nn-os.org there are many tutorials and research papers for you to educate yourself. 

 

Neural Networks and Petri Nets are not trivial and require serious learning curve

I't's all great and pinky ... I'll skip.