High-Speed Reservoir Computing With Integrated Laser Graded Artificial Neurons

So-called neuromorphic computing involves the use of physical artificial neurons to do computing in a way that is inspired by the human brain. With photonic neuromorphic computing these artificial neurons generally use laser sources and structures such as micro-ring resonators and resonant tunneling diodes to inject photons and modulate them akin to biological neurons.

General reservoir computing with laser graded neuron. (Credit: Yikun Nie et al., 2024, Optica)

One limitation of photonic artificial neurons was that these have a binary response and a refractory period, making them unlike the more versatile graded neurons. This has now been addressed by [Yikun Nie] et al. with their research published inĀ Optica.

The main advantage of graded neurons is that they are capable of analog graded responses, combined with no refractory period in which the neuron is unresponsive. For the photonic version, a quantum dot (QD) based gain section was constructed, with the input pulses determining the (analog) output.

Multiple of these neurons were then combined on a single die, for use in a reservoir computing configuration. This was used with a range of tests, including arrhythmia detection (98% accuracy) and handwriting classification (92% accuracy). By having the lasers integrated and the input pulses being electrical in nature, this should make it quite low-power, as well as fast, featuring 100 GHz QD lasers.

Ecological System Dynamics For Computing

Some of you may remember that the ship’s computer on Star Trek: Voyager contained bioneural gel packs. Researchers have taken us one step closer to a biocomputing future with a study on the potential of ecological systems for computing.

Neural networks are a big deal in the world of machine learning, and it turns out that ecological dynamics exhibit many of the same properties. Reservoir Computing (RC) is a special type of Recurrent Neural Network (RNN) that feeds inputs into a fixed-dynamics reservoir black box with training only occurring on the outputs, drastically reducing the computational requirements of the system. With some research now embodying these reservoirs into physical objects like robot arms, the researchers wanted to see if biological systems could be used as computing resources.

Using both simulated and real bacterial populations (Tetrahymena thermophila) to respond to temperature stimuli, the researchers showed that ecological system dynamics has the “necessary conditions for computing (e.g. synchronized dynamics in response to the same input sequences) and can make near-future predictions of empirical time series.” Performance is currently lower than other forms of RC, but the researchers believe this will open up an exciting new area of research.

If you’re interested in some other experiments in biocomputing, checkout these RNA-based logic gates, this DNA-based calculator, or this fourteen-legged state machine.