Re:Neuromorphic computing implementation of pole balancing
by throwaway287391 on Sunday September 11, 2016 @07:47PM
(#12476309)
> "A Deep Learning system does not have a temporal component" but isnt that what recursive deep learning is for.
Yes, recurrent nets exist, and have since the 80s, before even convolutional nets. The authors seem a bit out of the loop, considering the (more recent) success of RNNs in speech recognition... Arguably this article itself describes a type of RNN.
Re:Neuromorphic computing implementation of pole balancing
by kleebeesh on Sunday September 11, 2016 @04:46PM
(#12475626)
Roughly speaking, low/middle/high are just buckets, each of which represents a third of the distribution for position, velocity, or angle.
We attempt to illustrate that in this image: http://neuromorphic.eecs.utk.edu/images/graphics/Inv-Example...
And how do they calibrate low/middle/high.