Diffractive optical networks use object shifts for performance boost
The Californer/10231006

LOS ANGELES - Californer -- Optical computing has been gaining wide interest for machine learning applications because of the massive parallelism and bandwidth of optics. Diffractive networks provide one such computing paradigm based on the transformation of the input light as it diffracts through a set of spatially-engineered surfaces, performing computation at the speed of light propagation without requiring any external power apart from the input light beam. Among numerous other applications, diffractive networks have been demonstrated to perform all-optical classification of input objects.

Researchers at the University of California, Los Angeles (UCLA), led by Professor Aydogan Ozcan, have introduced a 'time-lapse' scheme to significantly improve the image classification accuracy of diffractive optical networks on complex input objects. In this scheme, the object and/or the diffractive network are moved relative to each other during the exposure of the output detectors. Such a 'time-lapse' scheme has previously been used to achieve super-resolution imaging, for example, in security cameras, by capturing multiple images of a scene with lateral movements of the camera. Drawing inspiration from the success of time-lapse super-resolution imaging, UCLA researchers have utilized 'time-lapse diffractive networks' to achieve >62% blind testing accuracy on the all-optical classification of CIFAR-10 images, a publicly available dataset containing images of airplanes, cars, cats, etc. Their results achieved a significant improvement over the time-static diffractive optical networks.

More on The Californer

• Car Wash Deal in Downey CA Prices Starting from $8
• Dr. Vincent Malfitano Elected to Central Council of The Italian Catholic Federation, National Gov
• Your Body Isn't Broken—It's Out of Balance: The New Book Revealing the Blueprint to Restore Hormone Balance, Sleep, Gut & Metabolic Health
• Long Beach Recognizes September as National Preparedness Month, Relaunches Program to Connect Neighborhoods to Disaster Planning Resources
• SEEAG Adds Santa Barbara County Office, Student & Community Agriculture Learning Programs

The same research group previously demonstrated ensemble learning of diffractive networks, where several diffractive networks operated in unison to improve image classification accuracy. However, with the incorporation of the 'time-lapse' scheme, it is possible to outdo an ensemble of >15 networks with a single standalone diffractive network, significantly reducing the footprint of the diffractive system while eliminating the complexities of physical alignment and synchronization of several individual networks. The researchers also explored the incorporation of ensemble learning into time-lapse image classification, which revealed >65% blind testing accuracy in classifying CIFAR-10 images.

For the physical implementation of the presented time-lapse classification scheme, the simplest method would exploit the natural jitter of the objects or the diffractive camera during imaging and allow the benefit of time-lapse to be reaped with no additional cost apart from a slight increase in the inference time due to detector signal integration during the jitter.

More on The Californer

• California claims victory – again – over Huntington Beach as appeals court rules against city's NIMBY violations of state law
• The Great Junk Hunt Returns to Roseville – A Vintage Shopping Adventure Awaits!
• Erdos Technologies CEO Dan Herbatschek Emphasizes the Importance of Software in Helping Companies Make More Intelligent Decisions on Inventory Flow and Management
• MyNamePlayer Empowers Educators to Create Inclusive Classrooms Through Correct Name Pronunciation
• Long Beach Seeks Volunteers for 41st Annual California Coastal Cleanup Day, September 20

This research on time-lapse image classification is a demonstration of utilizing the temporal degrees of freedom of optical fields for optical computing and presents a large step forward toward all-optical spatiotemporal information processing with compact, low-cost and passive materials.

Reference: Md Sadman Sakib Rahman and Aydogan Ozcan, Time-lapse image classification using a diffractive neural network, Advanced Intelligent Systems (2023). https://doi.org/10.1002/aisy.202200387