All-optical machine learning using diffractive deep neural networks
All-optical machine learning using diffractive deep neural networks
"""
Here we introduce an all-optical deep learning framework, where the neural network is physically formed by multiple layers of diffractive surfaces that work in collaboration to optically perform an arbitrary function that the network can statistically learn. We term this framework as Diffractive Deep Neural Network (D2NN) and demonstrate its learning capabilities through both simulations and experiments. A D2NN can be physically created by using several transmissive and/or reflective layers, where each point on a given layer represents an
artificial neuron that is connected to other neurons of the following layers through optical diffraction (see Fig. 1A). Following the Huygens’ Principle, our terminology is based on the fact that each point on a given layer acts as a secondary source of a wave, the amplitude and phase of which are determined by the product of the input wave and the complex-valued transmission or reflection coefficient at that point. Therefore, an artificial neuron in a diffractive deep neural network is connected to other neurons of the following layer through a secondary wave that is modulated in amplitude and phase by both the input interference pattern created by the earlier layers and the local transmission/reflection coefficient at that point.
[...]
This D2NN design [can be] physically fabricated using e.g., 3D-printing, lithography, etc. To experimentally validate [...] we used terahertz (THz) part of the electromagnetic spectrum and a standard 3D-printer to fabricate different layers [...] we focused on transmissive D2NN architectures (Fig. 1) with phase-only modulation at each layer. For example, using five 3D-printed transmission layers, containing a total of 0.2 million neurons and ~8.0 billion connections [...] This D2NN design formed a fully-connected network and achieved 91.75% classification accuracy on MNIST dataset
[...]
using different 3D-printed layers, we experimentally demonstrated the function of an imaging lens using five transmissive layers with 0.45 million neurons that are stacked in 3D. This second 3D-printed D2NN was much more compact in depth, with 4 mm axial spacing between successive network layers, and that is why it had much smaller number of connections (<0.1 billion) among neurons compared to the digit classifier D2NN, which had 30 mm axial spacing between its layers.
"""
http://science.sciencemag.org/content/early/2018/07/25/science.aat8084
http://science.sciencemag.org/content/early/2018/07/25/science.aat8084

Labels: Oleg Zabluda

- posted by Oleg Zabluda @ 8:33 PM | permalink | | | technorati | bloglines | feedster

 
The National Association of Manufacturers (NAM) has issued a report that shows the macroeconomic impact of federal...
The National Association of Manufacturers (NAM) has issued a report that shows the macroeconomic impact of federal regulations.
"""
Total cost of federal regulations in 2012 was $2.028 trillion (in 2014 dollars). The annual cost burden for an average U.S. firm is $233,182, or 21 percent of average payroll. Eighty-eight percent of those surveyed say that federal regulations are a top challenge for their firm.
[...]
regulations costs breakdown into four main categories (in billions of dollars):

Economic: $1,448
Environmental: $330
Occupational Safety/Heath & Homeland Security: $92
Tax Compliance: $159
[...]
The analysis finds that the average U.S. company pays $9,991 per employee per year to comply with federal regulations. The average manufacturer in the United States pays nearly double that amount—$19,564 per employee per year. Small manufacturers, or those with fewer than 50 employees, incur regulatory costs of $34,671 per employee per year.
"""
http://www.nam.org/Special/Total-Cost-of-Regulation.aspx

http://www.nam.org/Special/Total-Cost-of-Regulation.aspx

Labels: Oleg Zabluda

- posted by Oleg Zabluda @ 6:47 PM | permalink | | | technorati | bloglines | feedster