Scale-, shift- and rotation-invariant diffractive optical networks

by   Deniz Mengu, et al.

Recent research efforts in optical computing have gravitated towards developing optical neural networks that aim to benefit from the processing speed and parallelism of optics/photonics in machine learning applications. Among these endeavors, Diffractive Deep Neural Networks (D2NNs) harness light-matter interaction over a series of trainable surfaces, designed using deep learning, to compute a desired statistical inference task as the light waves propagate from the input plane to the output field-of-view. Although, earlier studies have demonstrated the generalization capability of diffractive optical networks to unseen data, achieving e.g., >98 accuracy for handwritten digits, these previous designs are in general sensitive to the spatial scaling, translation and rotation of the input objects. Here, we demonstrate a new training strategy for diffractive networks that introduces input object translation, rotation and/or scaling during the training phase as uniformly distributed random variables to build resilience in their blind inference performance against such object transformations. This training strategy successfully guides the evolution of the diffractive optical network design towards a solution that is scale-, shift- and rotation-invariant, which is especially important and useful for dynamic machine vision applications in e.g., autonomous cars, in-vivo imaging of biomedical specimen, among others.



There are no comments yet.


page 22

page 23

page 24

page 26

page 27

page 28


Misalignment Resilient Diffractive Optical Networks

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

All-Optical Information Processing Capacity of Diffractive Surfaces

Precise engineering of materials and surfaces has been at the heart of s...

Design of Task-Specific Optical Systems Using Broadband Diffractive Neural Networks

We report a broadband diffractive optical neural network design that sim...

Ensemble learning of diffractive optical networks

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

Classification and reconstruction of spatially overlapping phase images using diffractive optical networks

Diffractive optical networks unify wave optics and deep learning to all-...

All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces

We report the design of diffractive surfaces to all-optically perform ar...
This week in AI

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