Tag Archives: Chee Wei Wong

A couple of proposed solutions to AI’s insatiable need for power?

Leave a reply

I have two stories about research into making artificial intelligence (AI) less wasteful of power. One is from the International Society for Optics and Photonics (SPIE) and the other from the Politecnico di Milano (Polytechnic of Milan).

International Society for Optics and Photonics (SPIE)

A September 9, 2025 news item on ScienceDaily announced a more energy efficient AI chip,

Artificial intelligence (AI) systems are increasingly central to technology, powering everything from facial recognition to language translation. But as AI models grow more complex, they consume vast amounts of electricity — posing challenges for energy efficiency and sustainability. A new chip developed by researchers at the University of Florida could help address this issue by using light, rather than just electricity, to perform one of AI’s most power-hungry tasks. Their research is reported in Advanced Photonics.

…

A September 8, 2025 SPIE (International Society for Optics and Photonics) press release, which originated the news item, provides more detail about the work, Note: Links have been removed,

The chip is designed to carry out convolution operations, a core function in machine learning that enables AI systems to detect patterns in images, video, and text. These operations typically require significant computing power. By integrating optical components directly onto a silicon chip, the researchers have created a system that performs convolutions using laser light and microscopic lenses—dramatically reducing energy consumption and speeding up processing.

“Performing a key machine learning computation at near zero energy is a leap forward for future AI systems,” said study leader Volker J. Sorger, the Rhines Endowed Professor in Semiconductor Photonics at the University of Florida. “This is critical to keep scaling up AI capabilities in years to come.”

In tests, the prototype chip classified handwritten digits with about 98 percent accuracy, comparable to traditional electronic chips. The system uses two sets of miniature Fresnel lenses—flat, ultrathin versions of the lenses found in lighthouses—fabricated using standard semiconductor manufacturing techniques. These lenses are narrower than a human hair and are etched directly onto the chip.

To perform a convolution, machine learning data is first converted into laser light on the chip. The light passes through the Fresnel lenses, which carry out the mathematical transformation. The result is then converted back into a digital signal to complete the AI task.

…

“This is the first time anyone has put this type of optical computation on a chip and applied it to an AI neural network,” said Hangbo Yang, a research associate professor in Sorger’s group at UF and co-author of the study.

The team also demonstrated that the chip could process multiple data streams simultaneously by using lasers of different colors—a technique known as wavelength multiplexing. “We can have multiple wavelengths, or colors, of light passing through the lens at the same time,” Yang said. “That’s a key advantage of photonics.”

The research was conducted in collaboration with the Florida Semiconductor Institute, UCLA [University of California at Los Angeles], and George Washington University. Sorger noted that chip manufacturers such as NVIDIA already use optical elements in some parts of their AI systems, which could make it easier to integrate this new technology.

“In the near future, chip-based optics will become a key part of every AI chip we use daily,” Sorger said. “And optical AI computing is next.”

…

There’s also a September 8, 2025 University of Florida news release (also on EurekAlert), which is similar to the one issued by SPIE.

The paper has been published on two different sites; the citation for the paper remains the same and there are links to two different sites hosting the paper,

Near-energy-free photonic Fourier transformation for convolution operation acceleration by Hangbo Yang, Nicola Peserico, Shurui Li, Xiaoxuan Ma, Russell L. T. Schwartz, Mostafa Hosseini, Aydin Babakhani, Chee Wei Wong, Puneet Gupta, Volker J. Sorger SPIE Digital library or Advanced Photonics Vol. 7, Issue 5, 056007 (2025) DOI: 10.1117/1.AP.7.5.056007

Both sites offer open access to the paper.

Politecnico di Milano (Polytechnic of Milan)

Caption: The photonic microchip (below) developed for the study on physical neural networks, along with the electronic chip (above, the yellow one) of control. Credit: Politecnico di Milano, DEIB – Department of Electronics, Information and Bioengineering

A September 12, 2025 Politecnico di Milano (Polytechnic of Milan) press release (also on EurekAlert but published September 9, 2025) announces work into a more energy efficient way to train artificial intelligence, specifically physical neural networks,

Artificial intelligence is now part of our daily lives, with the subsequent pressing need for larger, more complex models. However, the demand for ever-increasing power and computing capacity is rising faster than the performance traditional computers can provide.

To overcome these limitations, research is moving towards innovative technologies such as physical neural networks, analogue circuits that directly exploit the laws of physics (properties of light beams, quantum phenomena) to process information. Their potential is at the heart of the study published by the prestigious journal Nature. It is the outcome of collaboration between several international institutes, including the Politecnico di Milano, the École Polytechnique Fédérale in Lausanne, Stanford University, the University of Cambridge, and the Max Planck Institute.

The article entitled “Training of Physical Neural Networks” discusses the steps of research on training physical neural networks, carried out with the collaboration of Francesco Morichetti, professor at DEIB – Department of Electronics, Information and Bioengineering, and head of the university’s Photonic Devices Lab.

Politecnico di Milano contributed to this study by developing photonic chips for the creation of neural networks, exploiting integrated photonic technologies. Mathematical operations, such as sums and multiplications, can now be performed through light interference mechanisms on silicon microchips barely a few square millimetres in size.

“By eliminating the operations required for the digitisation of information, our photonic chips allow calculations to be carried out with a significant reduction in both energy consumption and processing time,” says Francesco Morichetti. A step forward to make artificial intelligence (which relies on extremely energy-intensive data centres) more sustainable.

The study published in Nature addresses the theme of training, precisely the phase in which the network learns to perform certain tasks. «With our research within the Department of Electronics, Information and Bioengineering, we have helped develop an “in-situ” training technique for photonic neural networks, i.e. without going through digital models. The procedure is carried out entirely using light signals. Hence, network training will not only be faster, but also more robust and efficient», adds Morichetti.

The use of photonic chips will allow the development of more sophisticated models for artificial intelligence, or devices capable of processing real-time data directly on site – such as autonomous cars or intelligent sensors integrated into portable devices – without requiring remote processing.

Here’s a link to and a citation for the paper,

Training of physical neural networks by Ali Momeni, Babak Rahmani, Benjamin Scellier, Logan G. Wright, Peter L. McMahon, Clara C. Wanjura, Yuhang Li, Anas Skalli, Natalia G. Berloff, Tatsuhiro Onodera, Ilker Oguz, Francesco Morichetti, Philipp del Hougne, Manuel Le Gallo, Abu Sebastian, Azalia Mirhoseini, Cheng Zhang, Danijela Marković, Daniel Brunner, Christophe Moser, Sylvain Gigan, Florian Marquardt, Aydogan Ozcan, Julie Grollier, Andrea J. Liu, Demetri Psaltis, Andrea Alù, Romain Fleury. Nature volume 645, pages 53–61 (2025) DOI: https://doi.org/10.1038/s41586-025-09384-2 Published: 03 September 2025 Version of record: 03 September 2025 Issue date: 04 September 2025

This paper is behind a paywall.

New paradigm for low power telecommunications

Leave a reply

I’m always a sucker for the nonlinear although I’m much more familiar with nonlinear narratives than I am with nonlinear photonics. From the July 15, 2012 news item on EurekAlert,

New research by Columbia Engineering demonstrates remarkable optical nonlinear behavior of graphene that may lead to broad applications in optical interconnects and low-power photonic integrated circuits. With the placement of a sheet of graphene just one-carbon-atom-thick, the researchers transformed the originally passive device into an active one that generated microwave photonic signals and performed parametric wavelength conversion at telecommunication wavelengths.

“We have been able to demonstrate and explain the strong nonlinear response from graphene, which is the key component in this new hybrid device,” says Tingyi Gu, the study’s lead author and a Ph.D. candidate in electrical engineering. “Showing the power-efficiency of this graphene-silicon hybrid photonic chip is an important step forward in building all-optical processing elements that are essential to faster, more efficient, modern telecommunications. And it was really exciting to explore the ‘magic’ of graphene’s amazingly conductive properties and see how graphene can boost optical nonlinearity, a property required for the digital on/off two-state switching and memory.”

Here’s one of the issues that scientists have been grappling with,

Until recently, researchers could only isolate graphene as single crystals with micron-scale dimensions, essentially limiting the material to studies confined within laboratories. “The ability to synthesize large-area films of graphene has the obvious implication of enabling commercial production of these proven graphene-based technologies,” explains James Hone, associate professor of mechanical engineering, whose team provided the high quality graphene for this study. “But large-area films of graphene can also enable the development of novel devices and fundamental scientific studies requiring graphene samples with large dimensions. This work is an exciting example of both—large-area films of graphene enable the fabrication of novel opto-electronic devices, which in turn allow for the study of scientific phenomena.”

Building on the work done by scientists such as Hone,this new group of researchers led by by Chee Wei Wong, professor of mechanical engineering, director of the Center for Integrated Science and Engineering, and Solid-State Science and Engineering at Columbia University, created a new device,

They have engineered a graphene-silicon device whose optical nonlinearity enables the system parameters (such as transmittance and wavelength conversion) to change with the input power level. The researchers also were able to observe that, by optically driving the electronic and thermal response in the silicon chip, they could generate a radio frequency carrier on top of the transmitted laser beam and control its modulation with the laser intensity and color. Using different optical frequencies to tune the radio frequency, they found that the graphene-silicon hybrid chip achieved radio frequency generation with a resonant quality factor more than 50 times lower than what other scientists have achieved in silicon.

“We are excited to have observed four-wave mixing in these graphene-silicon photonic crystal nanocavities,” says Wong. “We generated new optical frequencies through nonlinear mixing of two electromagnetic fields at low operating energies, allowing reduced energy per information bit. This allows the hybrid silicon structure to serve as a platform for all-optical data processing with a compact footprint in dense photonic circuits.”

That bit about the system parameters changing with input levels suggests a biological system responding sensitively to environmental inputs, e.g., when it gets hot, your body tries to cool itself down in a sensitive response to an input. Of course, that fanciful analogy doesn’t extend itself too far since the human body is trying to return to its internal balance point (homeostasis) which isn’t what the Columbia researchers are attempting to do with their device.