Gabriel Béna

Hey! I’m Gabriel — a postdoc at the Institute of Neuroinformatics in Zurich (INI), in Melika Payvand’s lab, and until recently a part-time neuromorphic researcher at SpiNNcloud Systems. Before Zurich, I completed my PhD at Imperial College London (Neural Reckoning Group, supervised by Prof. Dan Goodman) on modularity and self-organisation in neural networks. I bounce around between computational neuroscience, machine learning, and neuromorphic engineering, mostly chasing one question: how can a complex, adaptive and generally interesting intelligence emerge from physical computational substrates?

A lot of my work pokes at the structure–function relationship in neural networks. Turns out structural modularity alone doesn’t buy you functional specialisation — you need the right resource constraints and the right kind of input statistics for the two to actually line up. I’m now extending this on physical substrates, looking at how spatial and energy constraints, particularly in memristive neuromorphic hardware, can naturally push networks toward modular, compositional solutions.

In parallel, I’m fascinated by self-organising systems as a sandbox for thinking about how intelligence might grow from local rules. I’ve been training continuous Neural Cellular Automata to behave as a universal computational medium, and more recently flipped the framing — letting an NCA-like policy grow and self-repair digital Boolean circuits via purely local message passing (no global backprop required !).

On the side, I’ve also worked on Spiking Neural Networks (multimodal integration in particular) and helped develop the SNN software stack for SpiNNaker2.

The common thread? Modularity, robustness, and intelligence as emergent phenomena — things that grow out of the tension between constraints and goals, between local rules and global behaviour.

latest posts

May 12, 2025	A Path to Universal Neural Cellular Automata

selected publications

Dynamics of specialization in neural modules under resource constraints

Gabriel Béna and Dan F. M. Goodman

Nature Communications, 2025

Abs DOI Bib

The brain is structurally and functionally modular, although recent evidence has raised questions about the extent of both types of modularity. Using a simple, toy artificial neural network setup that allows for precise control, we find that structural modularity does not in general guarantee functional specialization (across multiple measures of specialization). Further, in this setup (1) specialization only emerges when features of the environment are meaningfully separable, (2) specialization preferentially emerges when the network is strongly resource-constrained, and (3) these findings are qualitatively similar across several different variations of network architectures. Finally, we show that functional specialization varies dynamically across time, and these dynamics depend on both the timing and bandwidth of information flow in the network. We conclude that a static notion of specialization is likely too simple a framework for understanding intelligence in situations of real-world complexity, from biology to brain-inspired neuromorphic systems.
@article{bena_dynamics_2025, title = {Dynamics of specialization in neural modules under resource constraints}, author = {Béna, Gabriel and Goodman, Dan F. M.}, journal = {Nature Communications}, volume = {16}, number = {1}, pages = {187}, year = {2025}, publisher = {Nature Publishing Group}, url = {https://www.nature.com/articles/s41467-024-55188-9}, doi = {https://doi.org/10.1038/s41467-024-55188-9}, tags = {Modularity, specialization, Resource-constrained}, }
Event-based backpropagation on the neuromorphic platform SpiNNaker2

Gabriel Béna, Timo Wunderlich, Mahmoud Akl, and 3 more authors

NICE 2025 Proceedings, 2025

Abs DOI Bib

Neuromorphic computing aims to replicate the brain’s capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient training of neural networks on neuromorphic hardware requires the development of training algorithms that retain the sparsity of spike-based communication during training. Here, we report on the first implementation of event-based backpropagation on the SpiNNaker2 neuromorphic hardware platform. We use EventProp, an algorithm for event-based backpropagation in spiking neural networks (SNNs), to compute exact gradients using sparse communication of error signals between neurons. Our implementation computes multi-layer networks of leaky integrate-and-fire neurons using discretized versions of the differential equations and their adjoints, and uses event packets to transmit spikes and error signals between network layers. We demonstrate a proof-of-concept of batch-parallelized, on-chip training of SNNs using the Yin Yang dataset, and provide an off-chip implementation for efficient prototyping, hyper-parameter search, and hybrid training methods.
@article{bena_eventbased_2025, title = {Event-based backpropagation on the neuromorphic platform {SpiNNaker}2}, journal = {NICE 2025 Proceedings}, author = {Béna, Gabriel and Wunderlich, Timo and Akl, Mahmoud and Vogginger, Bernhard and Mayr, Christian and Gonzalez, Hector Andres}, year = {2025}, date = {2025-03-19}, url = {https://arxiv.org/abs/2412.15021v1}, doi = {https://doi.org/10.48550/arXiv.2412.15021}, tags = {Event-based backpropagation, SpiNNaker, Neuromorphic computing}, eventtitle = {Neuro Inspired Computational Elements Conference 2025} }