CINPLA / neuronify

An educational neural network app using the integrate-and-fire method.
http://ovilab.net/neuronify
GNU General Public License v3.0
54 stars 12 forks source link

Better documentation on visual inputs #206

Open davepruitt opened 2 years ago

davepruitt commented 2 years ago

For the life of me, I cannot get the visual inputs to fire reliably. I've tried orientation-selective receptive fields, center-surround receptive fields, and rectangular receptive fields. I am generating activity with my computer's camera, and I know it's connected to my camera because I can see the image from my camera through the receptive field.

But no matter what I do - whether I try to match the orientation/position of the receptive field, or create more/less movement, I cannot get the visual input node to fire reliably.

Can you create better documentation on how this node works?