A resistor that works in a similarly to nerve cells in the body could be used to build neural networks for machine learning.
Many large machine learning models rely on increasing amounts of processing power to achieve their results, but this has vast energy costs and produces large amounts of heat.
One proposed solution is analogue machine learning, which works like a brain by using electronic devices similar to neurons to act as the parts of the model. However, these devices have so far not been fast, small or efficient enough to provide advantages over digital machine learning.
Murat Open at the Massachusetts Institute of Technology and his colleagues have created a nanoscale resistor that transmits protons from one terminal to another. This functions a bit like a synapse, a connection between two neurons, where ions flow in one direction to transmit information. But these “artificial synapses” are 1000 times smaller and 10,000 times faster than their biological counterparts.
Just as a human brain learns by remodeling the connections between millions of interconnected neutrons, so too could machine learning models run on networks of these NATO resistors.
“We are doing somewhat similar things [in biology], like ion transport, but we are now doing it so fast, whereas biology couldn’t,” says One, whose device is a million times faster than previous proton-transporting devices.
The resistor uses powerful electric fields to transport protons at very high speeds without damaging or breaking the resistor itself, a problem previous solid-state proton resistors had suffered from.
For practical analogue machine learning, systems containing many millions of resistors will be required. One concedes that this is an engineering challenge, but the fact that the materials are all silicon-compatible should make it easier to integrate with existing computing architectures.
“For what they achieve in terms of technology – very high speed, low-energy and efficient – this looks really impressive,” says Sergey Saveliev at Lough borough University, UK. However, the fact that the device uses three terminals, rather than two as a human neuron does, might make it more difficult to run certain neural networks, he adds.
Pavel Boris, also at Lough borough University, agrees that it is an impressive technology, but he points out that the protons come from hydrogen gas, which could prove tricky to keep safely in the device when scaling up the technology.
A nanoscale rotor made from DNA could be used as a tiny valve for tasks like sorting molecules, or it could act as a switch in a biological computer.
Designing moving mechanical systems at nanoscale is difficult because of the random movements of small molecules, which knocks components back and forth. There are many examples of effective biological motors in nature, such as flatmate, an energy-producing enzyme with a central rotating column, but functioning synthetic nanometers had yet to be built.
Building devices at the nanoscale is difficult because small molecules move about randomly, but now researchers have made a working rotor using DNA
The minimum amount of energy needed for a computer to perform a computational step is called the “Landau limit”, named after the 1960s physicists Rolf Landau. In his calculations, landau did not consider any specific computer design, but rather the basic energy cost required to manipulate information, like erasing or re-writing a bit.
You must be logged in to post a comment.