Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Researchers move closer to completely optical artificial neural network

23.07.2018

Optical training of neural networks could lead to more efficient artificial intelligence

Researchers have shown that it is possible to train artificial neural networks directly on an optical chip. The significant breakthrough demonstrates that an optical circuit can perform a critical function of an electronics-based artificial neural network and could lead to less expensive, faster and more energy efficient ways to perform complex tasks such as speech or image recognition.


Researchers have shown a neural network can be trained using an optical circuit (blue rectangle in the illustration). In the full network there would be several of these linked together. The laser inputs (green) encode information that is carried through the chip by optical waveguides (black). The chip performs operations crucial to the artificial neural network using tunable beam splitters, which are represented by the curved sections in the waveguides. These sections couple two adjacent waveguides together and are tuned by adjusting the settings of optical phase shifters (red and blue glowing objects), which act like 'knobs' that can be adjusted during training to perform a given task.

Credit: Tyler W. Hughes, Stanford University

"Using an optical chip to perform neural network computations more efficiently than is possible with digital computers could allow more complex problems to be solved," said research team leader Shanhui Fan of Stanford University. "This would enhance the capability of artificial neural networks to perform tasks required for self-driving cars or to formulate an appropriate response to a spoken question, for example. It could also improve our lives in ways we can't imagine now."

An artificial neural network is a type of artificial intelligence that uses connected units to process information in a manner similar to the way the brain processes information. Using these networks to perform a complex task, for instance voice recognition, requires the critical step of training the algorithms to categorize inputs, such as different words.

Although optical artificial neural networks were recently demonstrated experimentally, the training step was performed using a model on a traditional digital computer and the final settings were then imported into the optical circuit. In Optica, The Optical Society's journal for high impact research, Stanford University researchers report a method for training these networks directly in the device by implementing an optical analogue of the 'backpropagation' algorithm, which is the standard way to train conventional neural networks.

"Using a physical device rather than a computer model for training makes the process more accurate," said Tyler W. Hughes, first author of the paper. "Also, because the training step is a very computationally expensive part of the implementation of the neural network, performing this step optically is key to improving the computational efficiency, speed and power consumption of artificial networks."

A light-based network

Although neural network processing is typically performed using a traditional computer, there are significant efforts to design hardware optimized specifically for neural network computing. Optics-based devices are of great interest because they can perform computations in parallel while using less energy than electronic devices.

In the new work, the researchers overcame a significant challenge to implementing an all-optical neural network by designing an optical chip that replicates the way that conventional computers train neural networks.

An artificial neural network can be thought of as a black box with a number of knobs. During the training step, these knobs are each turned a little and then the system is tested to see if the performance of the algorithms improved.

"Our method not only helps predict which direction to turn the knobs but also how much you should turn each knob to get you closer to the desired performance," said Hughes. "Our approach speeds up training significantly, especially for large networks, because we get information about each knob in parallel."

On-chip training

The new training protocol operates on optical circuits with tunable beam splitters that are adjusted by changing the settings of optical phase shifters. Laser beams encoding information to be processed are fired into the optical circuit and carried by optical waveguides through the beam splitters, which are adjusted like knobs to train the neural network algorithms.

In the new training protocol, the laser is first fed through the optical circuit. Upon exiting the device, the difference from the expected outcome is calculated. This information is then used to generate a new light signal, which is sent back through the optical network in the opposite direction. By measuring the optical intensity around each beam splitter during this process, the researchers showed how to detect, in parallel, how the neural network performance will change with respect to each beam splitter's setting. The phase shifter settings can be changed based on this information, and the process may be repeated until the neural network produces the desired outcome.

The researchers tested their training technique with optical simulations by teaching an algorithm to perform complicated functions, such as picking out complex features within a set of points. They found that the optical implementation performed similarly to a conventional computer.

"Our work demonstrates that you can use the laws of physics to implement computer science algorithms," said Fan. "By training these networks in the optical domain, it shows that optical neural network systems could be built to carry out certain functionalities using optics alone."

The researchers plan to further optimize the system and want to use it to implement a practical application of a neural network task. The general approach they designed could be used with various neural network architectures and for other applications such as reconfigurable optics.

###

Paper: T. W. Hughes, M. Minkov, Y. Shi, S. Fan, "Training of photonic neural networks through in situ backpropagation and gradient measurement," Optica, Volume 5,Issue , pages 864-871 (2018)

DOI: https://doi.org/10.1364/OPTICA.5.000864

About Optica

Optica is an open-access, online-only journal dedicated to the rapid dissemination of high-impact peer-reviewed research across the entire spectrum of optics and photonics. Published monthly by The Optical Society (OSA), Optica provides a forum for pioneering research to be swiftly accessed by the international community, whether that research is theoretical or experimental, fundamental or applied. Optica maintains a distinguished editorial board of more than 50 associate editors from around the world and is overseen by Editor-in-Chief Alex Gaeta, Columbia University, USA. For more information, visit Optica.

About The Optical Society

Founded in 1916, The Optical Society (OSA) is the leading professional organization for scientists, engineers, students and business leaders who fuel discoveries, shape real-life applications and accelerate achievements in the science of light. Through world-renowned publications, meetings and membership initiatives, OSA provides quality research, inspired interactions and dedicated resources for its extensive global network of optics and photonics experts. For more information, visit osa.org.

Media Contact:

Azalea Coste
acoste@osa.org

http://www.osa.org 

Azalea Coste | EurekAlert!
Further information:
http://dx.doi.org/10.1364/OPTICA.5.000864

Further reports about: artificial neural network neural network

More articles from Information Technology:

nachricht Open source software helps researchers extract key insights from huge sensor datasets
22.03.2019 | Universität des Saarlandes

nachricht Touchscreens go 3D with buttons that pulsate and vibrate under your fingertips
14.03.2019 | Universität des Saarlandes

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: The taming of the light screw

DESY and MPSD scientists create high-order harmonics from solids with controlled polarization states, taking advantage of both crystal symmetry and attosecond electronic dynamics. The newly demonstrated technique might find intriguing applications in petahertz electronics and for spectroscopic studies of novel quantum materials.

The nonlinear process of high-order harmonic generation (HHG) in gases is one of the cornerstones of attosecond science (an attosecond is a billionth of a...

Im Focus: Magnetic micro-boats

Nano- and microtechnology are promising candidates not only for medical applications such as drug delivery but also for the creation of little robots or flexible integrated sensors. Scientists from the Max Planck Institute for Polymer Research (MPI-P) have created magnetic microparticles, with a newly developed method, that could pave the way for building micro-motors or guiding drugs in the human body to a target, like a tumor. The preparation of such structures as well as their remote-control can be regulated using magnetic fields and therefore can find application in an array of domains.

The magnetic properties of a material control how this material responds to the presence of a magnetic field. Iron oxide is the main component of rust but also...

Im Focus: Self-healing coating made of corn starch makes small scratches disappear through heat

Due to the special arrangement of its molecules, a new coating made of corn starch is able to repair small scratches by itself through heat: The cross-linking via ring-shaped molecules makes the material mobile, so that it compensates for the scratches and these disappear again.

Superficial micro-scratches on the car body or on other high-gloss surfaces are harmless, but annoying. Especially in the luxury segment such surfaces are...

Im Focus: Stellar cartography

The Potsdam Echelle Polarimetric and Spectroscopic Instrument (PEPSI) at the Large Binocular Telescope (LBT) in Arizona released its first image of the surface magnetic field of another star. In a paper in the European journal Astronomy & Astrophysics, the PEPSI team presents a Zeeman- Doppler-Image of the surface of the magnetically active star II Pegasi.

A special technique allows astronomers to resolve the surfaces of faraway stars. Those are otherwise only seen as point sources, even in the largest telescopes...

Im Focus: Heading towards a tsunami of light

Researchers at Chalmers University of Technology and the University of Gothenburg, Sweden, have proposed a way to create a completely new source of radiation. Ultra-intense light pulses consist of the motion of a single wave and can be described as a tsunami of light. The strong wave can be used to study interactions between matter and light in a unique way. Their research is now published in the scientific journal Physical Review Letters.

"This source of radiation lets us look at reality through a new angle - it is like twisting a mirror and discovering something completely different," says...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

International Modelica Conference with 330 visitors from 21 countries at OTH Regensburg

11.03.2019 | Event News

Selection Completed: 580 Young Scientists from 88 Countries at the Lindau Nobel Laureate Meeting

01.03.2019 | Event News

LightMAT 2019 – 3rd International Conference on Light Materials – Science and Technology

28.02.2019 | Event News

 
Latest News

Solving the efficiency of Gram-negative bacteria

22.03.2019 | Life Sciences

Bacteria bide their time when antibiotics attack

22.03.2019 | Life Sciences

Open source software helps researchers extract key insights from huge sensor datasets

22.03.2019 | Information Technology

VideoLinks
Science & Research
Overview of more VideoLinks >>>