Hartung-Gorre Verlag
Inh.: Dr.
Renate Gorre D-78465
Konstanz Fon: +49 (0)7533 97227 Fax: +49 (0)7533 97228 www.hartung-gorre.de
|
S
|
Series in Signal and Information Processing, Vol. 38
edited by Hans-Andrea Loeliger
Hugo Aguettaz
Clockless
Computation:
On the Stable Dynamics of
Autonomous Spiking Neural
Networks
1st Edition 2026. XXII, 104 pages.
€ 64,00.
ISBN
978-3-86628-862-1
Abstract
Biological
neural systems operate asynchronously and lack a global clock. Their components
are relatively slow, noisy, and imprecise. Yet, despite these limitations, such
systems exhibit remarkable memory capacity and coordinate complex behaviors
with high temporal precision.
A
central challenge for autonomous networks, which is critical for sustained
memory and continuous information generation, arises from the absence of an
external regulatory drive. In the absence of a global clock, local timing
perturbations can accumulate and compound, ultimately disrupting the integrity
of information within the network dynamics.
This
thesis demonstrates that network dynamics can be made robust against such
degradation without reliance on a global clock. Extensive numerical simulations
indicate that, within appropriate parameter ranges, virtually any random target
spike train (or firing score1) can be robustly memorized and autonomously
reproduced across the network. Upon proper initialization, the network
preserves precise relative timing of (almost) all spikes across all neurons,
even with significant perturbations, acting globally as an error-correcting
system.
Empirical
results further indicate that the maximum duration of memorizable
content scales linearly with the number of inputs per neuron, provided these
inputs are sufficiently diverse. When parallel connections exist between the
same pair of neurons, this diversity can be achieved entirely through
heterogeneous transmission delays. Consequently, even a single-neuron network
with delayed self-connections can autonomously memorize and reproduce a complex
spike train.
In
all experiments, synaptic weights are computed offline by solving an ensemble
of convex optimization problems that enforce geometric constraints on each
neuron’s internal state. Specifically, the optimization ensures that the neuron’s
potential remains well below the firing threshold during silent periods and
intersects the threshold with a steep slope precisely at designated firing
times.
By
integrating these insights, this work bridges the gap between reliable system-level
computation and low-precision, noisy local components. Clockless
continuous-time networks can operate with global spike-level temporal stability
comparable to that of digital processors, thereby opening new perspectives for
neuromorphic engineering. Future efforts will focus on deriving temporally
local learning rules that can be implemented in autonomous hardware, minimizing
inter-synaptic communication to strictly adhere to the energy-efficiency
constraints inherent to neuromorphic systems.
1 Not a standard term.
Keywords:
spiking neural networks; temporal stability; error-correcting systems; clockless systems
About the author:
Born
1996 in La Garenne-Colombes, France, Hugo Aguettaz attended the Lycée de la Versoie in
Thonon-les-Bains, where he graduated with highest
honors in the Scientific Baccalauréat in 2014. He
then pursued his Bachelor of Science in Microengineering
at the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland, completing the
degree in 2018. By 2021, he had earned a Master of Science in Robotics at the
same institution. That same year, Hugo joined the Signal and Information
Processing Laboratory (ISI) at ETH Zurich, where he completed his PhD under the
supervision of Prof. Dr. H.-A. Loeliger in 2026.
His
scientific interests have been in the broad areas of signal processing, neural
computation, quantum information processing, and applied category theory. He
also maintains a strong technical interest in programming, advocating for Rust
due to its unique combination of memory safety, high performance, and
bare-metal efficiency.
Series / Reihe "Series in
Signal and Information Processing" im Hartung-Gorre Verlag
Direkt bestellen
bei / to order directly from
Hartung-Gorre Verlag / D-78465 Konstanz /
Germany
Telefon: +49
(0) 7533 97227
http://www.hartung-gorre.de eMail: verlag@hartung-gorre.de