The artificial neurons consist of phase-change materials, including germanium antimony telluride. These materials are the basis of re-writable Blu-ray discs. However, the neurons store analogue information, not digital.
The team applied a series of electrical pulses to the artificial neurons, which resulted in the progressive crystallisation of the phase-change material, ultimately causing the neuron to fire. This is the foundation for event-based computation.
IBM fellow Evangelos Eleftheriou said: “In the past 24 months, we have discovered new memory techniques, including projected memory, stored 3 bits per cell in phase-change memory for the first time, and now are demonstrating the powerful capabilities of phase-change-based artificial neurons, which can perform various computational primitives such as data-correlation detection and unsupervised learning at high speeds using very little energy.”
Imitating the versatile computational capabilities of large populations of neurons has always been a challenge because of the required level of density and power.
Meanwhile, IBM scientists have organised hundreds of artificial neurons into populations and used them to represent fast and complex signals. The artificial neurons can sustain billions of switching cycles, which would correspond to multiple years of operation at an update frequency of 100Hz. The energy required for each neuron update was less than 5pJ and the average power less than 120µW.
The team says that even a single neuron can be used to detect patterns and discover correlations in real-time streams of event-based data. Large populations of these nanoscale neurons could also be used in neuromorphic coprocessors with co-located memory and processing units.
