Piecewise quadratic optical neural network

1993 ◽  
Author(s):  
Sanjay S. Natarajan ◽  
David P. Casasent
Keyword(s):  
Neural Network ◽  
Optical Neural Network

scholarly journals Freely scalable and reconfigurable optical hardware for deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liane Bernstein ◽  
Alexander Sludds ◽  
Ryan Hamerly ◽  
Vivienne Sze ◽  
Joel Emer ◽  
...  
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Data Transfer ◽  
Power Delivery ◽  
Optical Data ◽  
Optical Multicast ◽  
Optical Neural Network ◽  
Fully Connected ◽  
Management Power

AbstractAs deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available compute power; however, efforts to continue to scale electronic processors are impeded by the costs of communication, thermal management, power delivery and clocking. To improve scalability, we propose a digital optical neural network (DONN) with intralayer optical interconnects and reconfigurable input values. The path-length-independence of optical energy consumption enables information locality between a transmitter and a large number of arbitrarily arranged receivers, which allows greater flexibility in architecture design to circumvent scaling limitations. In a proof-of-concept experiment, we demonstrate optical multicast in the classification of 500 MNIST images with a 3-layer, fully-connected network. We also analyze the energy consumption of the DONN and find that digital optical data transfer is beneficial over electronics when the spacing of computational units is on the order of $$>10\,\upmu $$ > 10 μ m.

Optical neural network based on synthetic photonic lattices

2021 ◽  
Author(s):  
Artem V. Pankov ◽  
Oleg S. Sidelnikov ◽  
Ilya D. Vatnik ◽  
Dmitry V. Churkin ◽  
Andrey A. Sukhorukov
Keyword(s):  
Neural Network ◽  
Photonic Lattices ◽  
Optical Neural Network

scholarly journals Theta function identities from optical neural network transformations

1993 ◽  
Vol 16 (4) ◽  
pp. 805-810
Author(s):  
E. Elizalde ◽  
A. Romeo
Keyword(s):  
Neural Network ◽  
Theta Function ◽  
Heisenberg Model ◽  
Symmetric Functions ◽  
New Approach ◽  
Jacobi Theta Function ◽  
Cylindrically Symmetric ◽  
Optical Neural Network ◽  
Theta Function Identities

We take a new approach to the generation of Jacobi theta function identities. It is complementary to the procedure which makes use of the evaluation of Parseval-like identities for elementary cylindrically-symmetric functions on computer holograms. Our method is more simple and explicit than this one, which was an outcome of the construction of neurocomputer architectures through the Heisenberg model.

Sign in / Sign up

Export Citation Format

Share Document