News for hackers. Stuff that matters.
Re:All-optical machine learning using diffractive deep neura... by andrewjrangel on Monday August 06, 2018 @12:48PM (#17699291)
Can someone help me Grok how the 3D printed Neural Networks back propagate? As I am trying to go through the paper they describe it as a pure optical approach, but what adjusts the refraction elements during the learning process?
Re:All-optical machine learning using diffractive deep neura... by flohrian on Monday August 06, 2018 @01:23PM (#17699650)
from the paper:

"[...] learnable network parameter that is iteratively adjusted during the training process of the diffractive network, using an error back-propagation method. After this numerical training phase implemented in a computer, the D^2NN design is fixed and the transmission/reflection coefficients of the neurons of all the layers are determined. This D^2NN design, once physically fabricated using e.g., 3D-printing, 3lithography, etc., can then perform, at the speed of light propagation, the specific task that it is trained for, using only optical diffraction and passive optical components/layers, creating an efficient and fast way of implementing machine learning tasks."

Re:All-optical machine learning using diffractive deep neura... by andrewjrangel on Monday August 06, 2018 @01:58PM (#17699952)
So the optical component is only the end result model of the NN? It isn't learning using the optics?
Re:All-optical machine learning using diffractive deep neura... by dekhn on Monday August 06, 2018 @03:27PM (#17700879)
Only indirectly. the physical device only does feedforward so they had to train it using tensorflow on a conventional device.
Re:All-optical machine learning using diffractive deep neura... by cheeko1234 on Friday August 10, 2018 @01:32PM (#17735227)
Check out this new article:

https://www.osa.org/en-us/about_osa/newsroom/news_releases/2...

They implemented a back propagation algorithm using just optical.

Re:All-optical machine learning using diffractive deep neura... by dqpb on Monday August 06, 2018 @02:14PM (#17700071)
Which is unfortunate, since learning is the compute intensive part
Re:All-optical machine learning using diffractive deep neura... by heyitsguay on Monday August 06, 2018 @01:15PM (#17699563)
Can't access the article, but the abstract reads like this is inference only. If that's so, this still could be useful. For instance, you could train a network somewhere else, then implement the learned function optically.