A research lab in France has developed a sonic event-driven object-localisation system using analogue in-memory neuromorphic computation, inspired by a barn owl’s brain! “Real-world sensory-processing applications require compact, low-latency, and low-power computing systems,” according to CEA-Leti. “Enabled by their in-memory, event-driven computing abilities, hybrid memristive-CMOS neuromorphic architectures provide an ideal hardware substrate for such tasks.”
In an owl, the difference between the arrival time of a sound in each ear is processed to locate the sound source in azimuth, its nervous system has an array of neurons able to detect time correlations between signal spikes, and the neuron that fires indicates the time difference and therefore the target angle. This auditory search is always on and takes very low power and when enough information has been received, it prompts the owl to start a more accurate but energy-hungry visual search. Biological event-driven sensing and analogue in-memory computing are critical.
“We drew inspiration from biology to incorporate these two aspects of computation into our hardware,” said CEA-Leti scientist Elisa Vianello. “In particular, we focused on the acoustic-based, object-localisation task. Owls efficiently solve this problem and thus we extrapolated their computational principles into our system.”
The electronic system merges 130nm CMOS with integrated hafnium-dioxide analogue resistive memory, which is matched to micromachined silicon piezoelectric ultrasound transducers under 1mm across, one 112kHz emitter, and a pair of receivers 100mm apart to model the owl’s ears. The team designed a pre-processing pipeline for each ‘ear’. Each channel gets a pre-amp, a band-pass filter, an envelope detecting rectifier and a threshold detector, which emulates a particular type of neuron and delivers a spike-like pulse once certain time and amplitude dependencies have been met from the envelope detector.
If the sound reflecting object is within the space of both ears, the pipeline delivers a spike on each channel whose time difference is related to the target azimuth angle. To detect time difference, each ear gets the equivalent of a tapped delay line into which its spike is fed. A long row of detectors is wired to the taps of the delay lines. The first detector is wired to the first tap of the left ear’s delay line and the last tap of the right ear. The next is wired to the second tap of the left ear and the penultimate tap of the right ear, and so on.
The result, due to the separate delays, is that for any particular time difference between the spikes from the left and right ears, only one detector gets its spikes simultaneously and is triggered, so the position of the triggered detector in the long row is directly related to the angle of the sound source to the ears hence more taps and detectors will increase the angular accuracy of the system. In the CEA-Leti device, the delay lines and coincidence detectors are implemented using resistive-ram-based neuromorphic circuits—non-volatile resistive ram stores the network’s synaptic weights for zero energy when the system is idle.
Low power consumption comes from the intrinsic way this arrangement computes asynchronously, and only when information arrives, compared with conventional processing where the detected signal is continuously sampled and processed to extract information. The lab claims that this auditory processing system is five orders of magnitude more energy-efficient “compared to conventional localisation systems”.
The article can be read here.
