Matthew Griffin, described as “The Adviser behind the Advisers” and a “Young Kurzweil,” is the founder and CEO of the 311 Institute, a global futures and deep futures consultancy working between the dates of 2020 to 2070, and is an award winning futurist, and author of “Codex of the Future.” Regularly featured in the global media, including AP, BBC, CNBC, Discovery, RT, and Viacom, Matthew’s ability to identify, track, and explain the impacts of hundreds of revolutionary emerging technologies on global culture, industry and society, is unparalleled. Recognised for the past six years as one of the world’s foremost futurists, innovation and strategy experts Matthew is an international speaker who helps governments, investors, multi-nationals and regulators around the world envision, build and lead an inclusive, sustainable future. A rare talent Matthew’s recent work includes mentoring Lunar XPrize teams, re-envisioning global education and training with the G20, and helping the world’s largest organisations envision and ideate the future of their products and services, industries, and countries. Matthew's clients include three Prime Ministers and several governments, including the G7, Accenture, Bain & Co, BCG, BOA, Blackrock, Bentley, Credit Suisse, Dell EMC, Dentons, Deloitte, Du Pont, E&Y, GEMS, HPE, Huawei, JPMorgan Chase, KPMG, McKinsey, PWC, Qualcomm, SAP, Samsung, Sopra Steria, UBS, and many more.
WHY THIS MATTERS IN BRIEF
There is nothing on Earth like the human brain, even today’s AI doesn’t come close, but now researchers have created an Artificial Synapse that’s 200 million times faster than a human synapse, and one day it will revolutionise AI and computing.
Researchers at the US based National Institute of Standards and Technology (NIST) have announced they’ve built an artificial synapse, or in their terminology, a superconducting switch, that can learn and record “memories” in the same way a human brain does, and the breakthrough could one day lead to the creation of neuromorphic, or “brain-like” computers that pack the power of today’s largest supercomputers into a chip the size of your fingernail.
Like its biological equivalent the NIST artificial synapse, which is described in Science Advances, is arguably the last piece in the jigsaw puzzle that scientists need to create the world’s first fully functional neuromorphic computer. Envisioned as a new type of Artificial Intelligence (AI) neuromorphic computers could boost computer’s perception and decision making capabilities, and benefit a huge range of applications, from self-driving cars to cancer research. They could also one day lead to the creation of Hollywood-esque “sentient” robots.
How The Artificial Synapse Works
A human synapse is a connection or switch between two brain cells, and NIST’s artificial synapse, which is a small, metallic cylinder just 10 micrometers in diameter, is like the real thing because it can process incoming electrical “spikes” that can customise spiking output signals. Putting this in layman terms in short they’ve now found a way to control the input and output intensities of the electrical spikes that go across the cylinder, or artificial synapse, in much the same way the human brain regulates similar electrical impulses as they cross our own synaptic junctions.
The team say this “spike management” is made possible by the use of “a flexible internal design that can be tuned by experience or its environment,” and the more electrical spikes, or “firing,” there is the stronger the connection, which means that one day neuromorphic chips will not just be able to maintain old circuits, but also create new ones in the same way our own brains do.
In a blow to human kind though the NIST artificial synapses are showing themselves to be better than the real thing, and in this case they’re much, much faster, being able to fire a billion times a second compared with our own brain’s poultry 50 times per second. Furthermore, and again as yet another blow to human kind they’ve crossed a magic threshold, they use one thousandth as much energy as a human synapse, and that was always one of the great technical challenges that teams around the world have been trying to solve for decades – how to create a powerful brain like computer that uses the same amount of energy to process information as the human brain which is staggeringly energy efficient. Basically your brain is running on the equivalent of two AA batteries – that’s energy efficiency for you.
In technical terms, the spiking energy is less than 1 attojoule and it’s on a par with the chemical energy bonding two atoms in a molecule together.
“The NIST synapse has lower energy needs than the human synapse, and we don’t know of any other artificial synapse that uses less energy,” said NIST physicist Mike Schneider.
The new synapse would be used in neuromorphic computers made of superconducting components, which can transmit electricity without resistance, making them some of, if not the most energy efficient computing platforms on the planet.
Data would be transmitted, processed and stored in units of magnetic flux, and while superconducting devices mimicking brain cells and transmission lines have been developed by researchers from institutions such as MIT, who recently showed off their own breakthrough, until now, efficient synapses, a crucial piece, have been missing.
The brain is especially powerful for tasks like context recognition because it processes data both in sequence and simultaneously and it stores memories in synapses all over the system, but a conventional computer processes data only in sequence and stores memory in a separate components, such as DRAM and storage, whereas a neuromorphic chip could do it all in situ, again like our own brains do.
The NIST artificial synapse is what’s known as a Josephson junction. These junctions are a sandwich of superconducting materials with an insulator as a filling. When an electrical current flowing through the junction exceeds a level called the critical current, voltage spikes are produced. The synapse uses standard Niobium electrodes but has a unique filling made of nanoscale clusters of manganese in a silicon matrix, and the nanoclusters, of which there are about 20,000 per square micrometer, act like tiny bar magnets with “spins” that can be oriented either randomly or in a coordinated manner.
“These are customized Josephson junctions,” Schneider said, “we can control the number of nanoclusters pointing in the same direction, which affects the superconducting properties of the junction.”
The synapse rests in a superconducting state, except when it’s activated by incoming current and starts producing voltage spikes. Researchers apply current pulses in a magnetic field to boost the magnetic ordering, that is, the number of nanoclusters pointing in the same direction. This magnetic effect progressively reduces the critical current level, making it easier to create a normal conductor and produce voltage spikes.
The critical current is the lowest when all the nanoclusters are aligned. The process is also reversible, pulses are applied without a magnetic field to reduce the magnetic ordering and raise the critical current. This design, in which different inputs alter the spin alignment and resulting output signals, is similar to how the brain operates.
The synapses behaviours can also be tuned by changing how the device is made and its operating temperature. By making the nanoclusters smaller, researchers can reduce the pulse energy needed to raise or lower the magnetic order of the device. Raising the operating temperature slightly from minus 271.15 degrees C (minus 456.07 degrees F) to minus 269.15 degrees C (minus 452.47 degrees F), for example, results in more and higher voltage spikes.
Crucially, the synapses can be stacked in 3D to make larger systems that could be used for computing and the NIST team created a circuit model to simulate how such a system would work.
The NIST synapse’s combination of small size, superfast spiking signals, low energy needs and 3D stacking capability could provide the means for a far more complex neuromorphic system than has been demonstrated with other technologies, according to the paper.
Brain like supercomputers the size of a fingernail? Imagine what you could do with that…