Search
Menu
Meadowlark Optics - SEE WHAT

On-Chip Photonic Synapse Mimics Workings of Neural Synapse

Facebook X LinkedIn Email
A photonic computer chip that imitates the way the brain’s synapses work to store and process information — only at speeds a thousand times faster than those of the human brain — could pave the way for computers that work in a way similar to the human brain, but with the speed and power efficiency of photonic systems.

A research team of scientists from Oxford, Münster and Exeter Universities has demonstrated a fully integrated all-photonic synapse based on phase-change materials (PCMs). The light-based synapse resembles the neural synapse at the physical level and can achieve synaptic plasticity compatible with Hebbian learning.

“Since synapses outnumber neurons in the brain by around 10,000 to 1, any brain-like computer needs to be able to replicate some form of synaptic mimic. That is what we have done here,” professor Wolfram Pernice from the University of Münster said.

The synapse uses PCMs combined with integrated silicon nitride waveguides. A waveguide with discrete PCM structures acts as the photonic synapse with the input and output of the waveguide connected with a pre-neuron and a post-neuron. An optical circulator is used for connecting the output of the synapse and the post-neuron and for applying optical pulses to alter the synaptic weight.

Low-energy optical transmission can be measured from the pre-neuron to the post-neuron, with the transmission level dependent on the synaptic weight. The synaptic weight can be set randomly by varying the number of optical pulses sent down the waveguide.

The on-chip biomimetic photonic synapse has both analog and cumulative programmability, essential requirements for neuromorphic computing. Using purely optical means to build the synapse allows for ultrafast operation speed and virtually unlimited bandwidth with no electrical interconnect power losses.


Gentec Electro-Optics Inc   - Measure Your Laser MR
In optical field simulations researchers demonstrated that the distribution of the electric field in the photonic synapse was much more homogeneous than in conventional waveguide designs.

Professor Harish Bhaskaran from Oxford said, “The development of computers that work more like the human brain has been a holy grail of scientists for decades. Via a network of neurons and synapses, the brain can process and store vast amounts of information simultaneously, using only a few tens of watts of power. Conventional computers can't come close to this sort of performance.”

The researchers believe that through the use of improved device designs and switching protocols, along with the use of alternative PCMs with lower switching powers, it could ultimately be possible to realize large-scale photonic neuromorphic networks similar in scale to state-of-the-art electronic neuromorphic computers. Future work might focus on the implementation of an on-chip "integrate and fire" neuron, which would complete the building blocks required to enable truly integrated, biologically inspired photonic computing paradigms.

“Electronic computers are relatively slow, and the faster we make them, the more power they consume. Conventional computers are also pretty ‘dumb,’ with none of the in-built learning and parallel processing capabilities of the human brain,” professor C. David Wright from the University of Exeter said.

“We tackle both of these issues here — not only by developing new brain-like computer architectures, but also by working in the optical domain to leverage the huge speed and power advantages of the upcoming silicon photonics revolution.” 

The research was published in Science Advances (doi: 10.1126/sciadv.1700160). 


Published: October 2017
Research & TechnologyeducationEuropeOpticsCommunicationssilicon photonicsphotonic synapseneural networksmicrochipBioScanBiophotonics

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.