Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks

by   Deniz Mengu, et al.

Optical machine learning offers advantages in terms of power efficiency, scalability and computation speed. Recently, an optical machine learning method based on diffractive deep neural networks (D2NNs) has been introduced to execute a function as the input light diffracts through passive layers, designed by deep learning using a computer. Here we introduce improvements to D2NNs by changing the training loss function and reducing the impact of vanishing gradients in the error back-propagation step. Using five phase-only diffractive layers, we numerically achieved a classification accuracy of 97.18 and 87.67 respectively; using both phase and amplitude modulation (complex-valued) at each layer, our inference performance improved to 97.81 respectively. Furthermore, we report the integration of D2NNs with electronic neural networks to create hybrid classifiers that significantly reduce the number of input pixels into an electronic network using an ultra-compact front-end D2NN with a layer-to-layer distance of a few wavelengths, also reducing the complexity of the successive electronic network. Using a 5-layer phase-only D2NN jointly-optimized with a single fully-connected electronic layer, we achieved a classification accuracy of 98.17 recognition of handwritten digits and fashion products, respectively. Moreover, the input to the electronic network was compressed by >7.8 times down to 10x10 pixels, making the jointly-optimized hybrid system perform classification with a simple electronic layer. Beyond creating low-power and high-frame rate ubiquitous machine learning platforms, such D2NN-based hybrid neural networks will find applications in optical imager and sensor design.



There are no comments yet.


page 26

page 27

page 29

page 35


All-Optical Machine Learning Using Diffractive Deep Neural Networks

We introduce an all-optical Diffractive Deep Neural Network (D2NN) archi...

Deep Learning Reconstruction of Ultra-Short Pulses

Ultra-short laser pulses with femtosecond to attosecond pulse duration a...

Ensemble learning of diffractive optical networks

A plethora of research advances have emerged in the fields of optics and...

Misalignment Resilient Diffractive Optical Networks

As an optical machine learning framework, Diffractive Deep Neural Networ...

Terahertz Pulse Shaping Using Diffractive Legos

Recent advances in deep learning have been providing non-intuitive solut...

Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy

Diffractive deep neural networks have been introduced earlier as an opti...

Single-Shot Optical Neural Network

As deep neural networks (DNNs) grow to solve increasingly complex proble...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.