New preprint (well, very updated). 🤖🧠🧪 We find that an abstract model of neuromodulation lets spiking neural networks perform much better, particularly in challenging noisy environments, using less energy. Relevant to #neuroscience and #neuromorphic computing. 🧵👇 www.biorxiv.org/content/10.1...

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.299Z

Our model is simple at the core: we let a modulatory neuron modify the underlying parameters of another neuron (like threshold or time constant), and train end to end. We can make this more realistic in various ways (different types of neuromodulators, spatial release and diffusion) - see later.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.300Z

With this model, performance at a variety of tasks goes up (in the picture, an auditory task). A small network with modulation performs much better than a much larger network without modulation. We can also see here that modulation at medium timescales is best. Spatial scale not very important here.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.301Z

The performance enhancement is particularly large in a noisy background, in the range where human speech recognition is much better than state-of-the-art automatic speech recognition systems.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.302Z

And we can understand how it's doing it: it dials up the sensitivity when the noise level is low, and dials it down when the noise is high. This sort of dynamic gain control is the "listening in the dips" strategy that has been hypothesised to be used by humans. We didn't put this in, it learned it!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.303Z

Our model allows for setting a number of neuromodulator types, that can have interactions between each other, and making neuromodulator release diffuse in space and time. This actually turns out to further improve performance!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.304Z

In a neuromorphic or machine learning context, neuromodulation is very parameter efficient. This figure shows every variant of the modulated and unmodulated models in our paper, comparing parameter count versus accuracy. You can see that the frontier of modulated networks is much higher.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.305Z

Modulation (top curve, red) also lets us reduce firing rates by orders of magnitude without hurting performance, unlike unmodulated networks (bottom curve, blue). Fewer spikes means less energy. Important both for real brains and neuromorphic devices!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.306Z

There's a lot more in the paper, so please do give it a read if any of these sound interesting. I think the headline results are that neuromodulation makes performance better with less energy. We also have a tutorial and code to integrate this into your models. neural-reckoning.org/pub_neuromod...

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.307Z

Neuromodulation enhances the capability and efficiency of spiking neural networks

AlKilany A, Goodman DFM
Preprint
 

Abstract

Spiking neurons underlie the brain's extreme energy efficiency, and therefore have great potential in neuromorphic computing, although realising this efficiency in practice has proven challenging. We use neuromodulation, a biological mechanism that lets the network dynamically and contextually modify its own parameters. We find it substantially increases performance across a range of sensory processing tasks, including a challenging new speech-in-noise dataset we introduce, with very few additional resources (neurons, energy, parameters). Neuromodulatory networks are space and energy efficient thanks to two mechanisms that are directly relevant to neuromorphic computing and biology: firstly, they allow for an order-of-magnitude reduction in the number of neurons required; and secondly, they enable very sparse firing, achieving better results using orders of magnitude fewer spikes. Together, these properties may throw light on the computational role of neuromodulation in biology, and make neuromodulation an ideal mechanism to improve performance and efficiency for neuromorphic devices.

Links

Categories

The short version

New preprint (well, very updated). 🤖🧠🧪 We find that an abstract model of neuromodulation lets spiking neural networks perform much better, particularly in challenging noisy environments, using less energy. Relevant to #neuroscience and #neuromorphic computing. 🧵👇 www.biorxiv.org/content/10.1...

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.299Z

Our model is simple at the core: we let a modulatory neuron modify the underlying parameters of another neuron (like threshold or time constant), and train end to end. We can make this more realistic in various ways (different types of neuromodulators, spatial release and diffusion) - see later.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.300Z

With this model, performance at a variety of tasks goes up (in the picture, an auditory task). A small network with modulation performs much better than a much larger network without modulation. We can also see here that modulation at medium timescales is best. Spatial scale not very important here.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.301Z

The performance enhancement is particularly large in a noisy background, in the range where human speech recognition is much better than state-of-the-art automatic speech recognition systems.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.302Z

And we can understand how it's doing it: it dials up the sensitivity when the noise level is low, and dials it down when the noise is high. This sort of dynamic gain control is the "listening in the dips" strategy that has been hypothesised to be used by humans. We didn't put this in, it learned it!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.303Z

Our model allows for setting a number of neuromodulator types, that can have interactions between each other, and making neuromodulator release diffuse in space and time. This actually turns out to further improve performance!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.304Z

In a neuromorphic or machine learning context, neuromodulation is very parameter efficient. This figure shows every variant of the modulated and unmodulated models in our paper, comparing parameter count versus accuracy. You can see that the frontier of modulated networks is much higher.

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.305Z

Modulation (top curve, red) also lets us reduce firing rates by orders of magnitude without hurting performance, unlike unmodulated networks (bottom curve, blue). Fewer spikes means less energy. Important both for real brains and neuromorphic devices!

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.306Z

There's a lot more in the paper, so please do give it a read if any of these sound interesting. I think the headline results are that neuromodulation makes performance better with less energy. We also have a tutorial and code to integrate this into your models. neural-reckoning.org/pub_neuromod...

— Dan Goodman (@neural-reckoning.org) 2026-07-16T17:29:03.307Z