Photonic Neural Network Can Store, Process Information Similarly to Human Brain

Facebook X LinkedIn Email
A new microchip contains a network of artificial neurons that works with light and can imitate the behavior of the human brain’s neurons and synapses. A research team from the University of Münster, University of Oxford, and University of Exeter demonstrated that the optical neurosynaptic network was able to learn information and use it as a basis for computing and recognizing patterns, similar to the way a human brain works.

Because the system functions solely with light, it can process data many times faster than a system that functions with electrons. Most existing approaches relating to so-called neuromorphic networks are based on electronics, the researchers said. Traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient computing difficult to achieve.

Optical neurosynaptic network, University of Munster.
Schematic illustration of a light-based, brain-inspired chip. By mimicking biological neuronal systems, photonic neuromorphic processors provide a promising platform to tackle challenges in machine learning and pattern recognition. Courtesy of the Fun-COMP project.

In the new chip, optical waveguides that can transmit light and be fabricated into optical microchips are integrated with phase-change materials like those found on storage media such as rewritable DVDs.

Phase-change materials can change their optical properties depending on whether they are crystalline or amorphous. In crystalline form, the atoms in the material arrange themselves in a regular fashion, but in amorphous form, the atoms organize themselves in an irregular way. This phase-change can be triggered by light if a laser heats up the material.

The scientists were able to merge many nanostructured phase-change materials into one neurosynaptic network. “Because the material reacts so strongly and changes its properties dramatically, it is highly suitable for imitating synapses and the transfer of impulses between two neurons,” said researcher Johannes Feldmann.

The researchers developed a chip with four artificial neurons and a total of 60 synapses. The structure of the chip consisted of different layers. The team used wavelength division multiplexing techniques to implement a scalable circuit architecture.

Optical neurosynaptic network, University of Munster.
he optical microchips that the researchers are developing are about the size of a one-cent piece. Courtesy of WWU Muenster/Peter Leßmann.

To test the extent to which the system was able to recognize patterns, the researchers fed it information in the form of light pulses, using two different machine learning algorithms for both supervised and unsupervised learning. The artificial network was ultimately able to recognize the pattern it was being trained to recognize on the basis of the light patterns it was fed.

“Our system has enabled us to take an important step toward creating computer hardware that behaves similarly to neurons and synapses in the brain and that is also able to work on real-world tasks,” said professor Wolfram Pernice.

“By working with photons instead of electrons we can exploit to the full the known potential of optical technologies — not only in order to transfer data, as has been the case so far, but also in order to process and store them in one place,” said professor Harish Bhaskaran. For example, with the aid of neurosynaptic hardware, cancer cells could be identified automatically.

Before such applications become reality, the researchers will need to increase the number of artificial neurons and synapses and increase the depth of the neural networks. This can be done, for example, with optical chips manufactured using silicon technology. Professor C. David Wright said that this step would be taken by using foundry processing for the production of nanochips as part of the EU joint project Fun-COMP.

The research was published in Nature ( 



Published: May 2019
machine learning
Machine learning (ML) is a subset of artificial intelligence (AI) that focuses on the development of algorithms and statistical models that enable computers to improve their performance on a specific task through experience or training. Instead of being explicitly programmed to perform a task, a machine learning system learns from data and examples. The primary goal of machine learning is to develop models that can generalize patterns from data and make predictions or decisions without being...
Optoelectronics is a branch of electronics that focuses on the study and application of devices and systems that use light and its interactions with different materials. The term "optoelectronics" is a combination of "optics" and "electronics," reflecting the interdisciplinary nature of this field. Optoelectronic devices convert electrical signals into optical signals or vice versa, making them crucial in various technologies. Some key components and applications of optoelectronics include: ...
Research & TechnologyOpticsneural networksmachine learningmedicalBiophotonicsCommunicationsoptoelectronicsTech Pulse

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.