Trending...
- California releases Master Plan to better support people with Autism and other developmental disabilities
- SMART PLUG: Intermittent Cold Compression Therapy Remote Patient Monitoring Artificial Intelligence System Announced at NextMed 2025
- Snell & Wilmer Associate Vivienne Chen Elected to Asian Pacific Community Fund Board of Directors
LOS ANGELES - Californer -- The bulk of the computing in state-of-the-art neural networks comprises linear operations, e.g., matrix-vector multiplications and convolutions. Linear operations can also play an important role in cryptography. While dedicated processors such as GPUs and TPUs are available for performing highly parallel linear operations, these devices are power-hungry, and the low bandwidth of electronics still limits their operation speed. Optics is better suited for such operations because of its inherent parallelism and large bandwidth and computation speed.
Built from a set of spatially engineered thin surfaces, diffractive deep neural networks (D2NN), also known as diffractive networks, form a recently emerging optical computing architecture capable of performing computational tasks passively at the speed of light propagation through an ultra-thin volume. These task-specific all-optical computers are designed digitally through learning of the spatial features of their constituent diffractive surfaces. Following this one-time design process, the optimized surfaces are fabricated and assembled to form the physical hardware of the diffractive optical network.
More on The Californer
In their recent publication in Advanced Photonics Nexus, a team of researchers led by Aydogan Ozcan, the Chancellor's Professor and the Volgenau Chair for Engineering Innovation at UCLA, has introduced a method to perform complex-valued linear operations with diffractive networks under spatially incoherent illumination. It had been shown previously by the same group that diffractive networks with sufficient degrees of freedom can perform arbitrary complex-valued linear transformations with spatially coherent light with negligible error. In contrast, with spatially incoherent light, these networks can perform arbitrary linear transformations of input optical intensities if the matrix elements defining the transformation are real and non-negative. Given that spatially incoherent illumination sources are more prevalent and easier to access, there is a growing need for spatially incoherent diffractive processors to handle data beyond just non-negative values.
More on The Californer
By incorporating preprocessing and postprocessing steps to represent complex numbers by a set of non-negative real numbers, UCLA researchers have extended the processing power of spatially incoherent diffractive networks to the domain of complex numbers. They demonstrated that such incoherent diffractive processors can be designed to perform an arbitrary complex-valued linear transformation with negligible error if there is a sufficient number of optimizable phase-only diffractive features within the design, which scales with the dimensions of the input and output complex vector spaces.
The researchers showcased the application of this novel scheme via encryption and decryption of complex-valued images using spatially incoherent diffractive networks. Apart from visual image encryption, such spatially incoherent diffractive processors could also be useful in other applications, e.g., in autonomous vehicles for ultra-fast and low-power processing of natural scenes.
Article: https://doi.org/10.1117/1.APN.3.1.016010
Built from a set of spatially engineered thin surfaces, diffractive deep neural networks (D2NN), also known as diffractive networks, form a recently emerging optical computing architecture capable of performing computational tasks passively at the speed of light propagation through an ultra-thin volume. These task-specific all-optical computers are designed digitally through learning of the spatial features of their constituent diffractive surfaces. Following this one-time design process, the optimized surfaces are fabricated and assembled to form the physical hardware of the diffractive optical network.
More on The Californer
- Spring Special: Say Goodbye to Lice Removal to a Convenient Location in Conroe, TX
- What they're saying: California's 25 key deliverables for 2025 to protect communities from wildfire
- Fingerpaint Group Boosts Market Access Capabilities with Acquisition of BlackPoint Consulting Group
- California: One year after launch, state's enhanced enforcement in Oakland recovers 3,217 stolen vehicles, arrests 1,823 suspects
- The Most Opulent Diamond Engagement Ring by Vikar Ahmed:Valued at an Extraordinary $2 to $2.5 Millio
In their recent publication in Advanced Photonics Nexus, a team of researchers led by Aydogan Ozcan, the Chancellor's Professor and the Volgenau Chair for Engineering Innovation at UCLA, has introduced a method to perform complex-valued linear operations with diffractive networks under spatially incoherent illumination. It had been shown previously by the same group that diffractive networks with sufficient degrees of freedom can perform arbitrary complex-valued linear transformations with spatially coherent light with negligible error. In contrast, with spatially incoherent light, these networks can perform arbitrary linear transformations of input optical intensities if the matrix elements defining the transformation are real and non-negative. Given that spatially incoherent illumination sources are more prevalent and easier to access, there is a growing need for spatially incoherent diffractive processors to handle data beyond just non-negative values.
More on The Californer
- Phonic Launches End-to-End Speech-to-Speech Platform for Building Reliable Voice Agents, Announces $4M Funding Raise
- HeartCraft: Gaming Charity Event Raising Money To Save Hearts
- Large Strategic Investment from Global Medical Device Manufacturer to Support Clinics Treating Suicidal Depression and PTSD: NRx: (Stock Symbol: NRXP)
- Lineus Medical Awarded Five Additional Patents
- Tired of Waiting Rooms? New HomeDoc Service Offers Australians Their Own Private Doctor
By incorporating preprocessing and postprocessing steps to represent complex numbers by a set of non-negative real numbers, UCLA researchers have extended the processing power of spatially incoherent diffractive networks to the domain of complex numbers. They demonstrated that such incoherent diffractive processors can be designed to perform an arbitrary complex-valued linear transformation with negligible error if there is a sufficient number of optimizable phase-only diffractive features within the design, which scales with the dimensions of the input and output complex vector spaces.
The researchers showcased the application of this novel scheme via encryption and decryption of complex-valued images using spatially incoherent diffractive networks. Apart from visual image encryption, such spatially incoherent diffractive processors could also be useful in other applications, e.g., in autonomous vehicles for ultra-fast and low-power processing of natural scenes.
Article: https://doi.org/10.1117/1.APN.3.1.016010
Source: ucla ita
Filed Under: Science
0 Comments
Latest on The Californer
- Ready Capital Corporation (RC) Investors Who Lost Money Have Opportunity to Lead Securities Fraud Lawsuit
- City of Long Beach Celebrates Earth Month with Events and Educational Campaigns Throughout April
- Benchmark International Faciltd. the Trans BT Power Maintenance Services and Platt Park
- Blenders Eyewear Appoints Jack Gray as Chief Executive Officer
- Mint Service Desk to Showcase Innovative ITSM Solutions at SITS 2025
- SAKKA Set to Distribute Masaaki Kudo's "A Far Shore" with Director's Commentary
- Rob Hock Tries to Help Struggling Stock Traders - Launches Spreadsheet
- "Pusherman" – The Real Story of Frank Lucas' Rise and Fall
- Trua SVP of Strategic Business Development Stuart Vaeth to Discuss Trust and Safety in the Gig Economy at Curbivore 2025
- Dominican Republic Gets Better For Car Rental Now that Zezgo Rent A Car Arrives At Punta Cana Airport
- AXWIFI 2.8 is Here: Advanced WiFi Management for Service Providers
- $19.8 Million Refinance Loan Secured for Prime Houston Property
- Live Courageously With Shawn Sourgose
- City of Long Beach Announces Operator for Long Beach Amphitheater
- California: ADVISORY: Governor Newsom to announce major skills-based hiring and education effort
- Minus K Congratulates to the following winners of their 2024/2025 Educational Giveaway
- Official Artwork Revealed for 39th Annual California Strawberry Festival
- Murder Mystery Audio Drama The Crime at Camp Ashwood Named Honoree In the 29th Annual Webby Awards
- Semtech Corporation (SMTC) Investors Who Lost Money Have Opportunity to Lead Securities Fraud Lawsuit
- Unlock the Benefits of Buying a Jersey Shore Home in Today's Market