Reducing the power consumption of neuromorphic AI systems

October 04, 2018 // By Nick Flaherty
Researchers in the US have developed a new class of device they call a memdiode that could provide more energy efficient computing for artificial intelligence in embedded systems rather than in the cloud. 

Teams from Binghamton University in New York and Georgia Tech have been working on switching devices that mimic the operation of human neurons called neuristors. Instead of using niobium dioxide (NbO2) to replicate the switching behaviour observed in ion channels within biological neurons, the team have used a metal-Nb2O5−x-metal structure they call a memdiode. This provides the rectification, hysteresis, and capacitance necessary for high density neuristor circuitry and is much esasier to make on standard CMOS process technology as it does not need to electroform a conducting filament or a large external capacitor.

This could lead to cheaper, more energy-efficient, and high-density neuristor circuits than previously possible, accelerating the way to more energy efficient and adaptable computing, says Louis Piper, associate professor of physics and director of materials science and engineering at Binghamton University (above).

The memdiode operates as a voltage threshold triggered switch so that the neuristor oscillates when the circuit is excited by a current. Initially, a capacitor is charged in parallel with one switch, and that switch turns on when a certain threshold voltage is reached. This switch will also turn off at a voltage lower than the turn-on voltage. When this first switch turns on, the voltage increases on a second memdiode/capacitor pair which causes the second memdiode to switch. This time delayed switching raises then lowers the voltage, creating an oscillatory pulse.

The memdiodes act in the same way as previous NbO2 threshold switches (both act as voltage threshold switches) with the added benefits of integrated capacitance and as-deposited switching. In this way two such memdiodes can form the basis of a neuristor by incorporating both the switching element and the capacitance into one device that does not require electroforming. Replicating a human brain requires 104 synapses per neuron and 106 neurons/cm2, so electroforming each individual NbO2 memristor becomes unfeasible.

Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.