Benchmarking the Connectomes of Caenorhabditis elegans within the Reservoir Computing Framework

Felix S. Reimers; Ola Huse Ramstad; Aliaksandr Hubin; Stefano Nichele

cs.LGSep 24, 2026

Benchmarking the Connectomes of Caenorhabditis elegans within the Reservoir Computing Framework

Authors: Felix S. Reimers, Ola Huse Ramstad, Aliaksandr Hubin, Stefano Nichele

Organizations: Department of Computer Science and Communication, Østfold University College, Halden, 1757, Østfold, Norway. · Faculty of Chemistry, Biotechnology and Food Science, Norwegian University of Life Sciences, ˚As, 1432, Akershus, Norway. · Department of Mathematics, University of Oslo, Oslo, 0316, Oslo, Norway.

Abstract

The aim of this work is to examine the connectomes of Caenorhabditis elegans through a computational lens using the reservoir computing framework. Connectomes are mappings of biological neural networks; C. elegans is the first organism for which physical connectomes covering the whole nervous system have been published. The connectomes of C. elegans used in this paper have been derived at different ages of the organism and are based on three different ways of measuring inter-cellular connections. They have, with minimal preprocessing, been implemented as reservoirs in the form of echo state networks, which are recurrent neural networks. In reservoir computing, the reservoir itself is not trained, rather the output of the reservoir is passed to a comparatively small read-out module in which training takes place. Training and testing is conducted in different neuro-inspired tasks, with the aim of using these tasks as a benchmark for the connectomes. This process has been repeated with different configurations of the reservoir and equally sized but randomized null models have been used for comparison. The results show that the biological wiring and a bio-informed configuration of input and output nodes of the reservoirs do not necessarily lead to better performance. Contrarily, the randomized null models are often outperforming the original connectomes on the chosen benchmarks. At the same time it becomes clear that the results depend a lot on the configuration of the reservoir and the way the connectome has been derived from the organism. Connectomes from different ages may produce varying outcome, without a clear trend becoming visible.

Figures & tables

Figure 1: The different hyperparameter and configuration choices that have been covered in the experiments. On the left of the figure it is described in which way the reservoirs are derived, on the right of the figure the conditions under which they are tested is depicted. A1a in Ages is color marked as here only the synapse count based connectome is available.

Figure 2: Conceptual depiction of an echo state network. Only the matrix W, connecting the reservoir to the read-out layer, is trained. Taken from Nichele and Molund (2017)

Figure 3: The performance of the connectomes based on the number of synapses and the corresponding null models. The rows correspond to the different tasks, the columns to the different reservoir configurations. In the individual plots, the model-based estimated means ± 95% CI is plotted against the age of the organism.

Figure 4: The performance of the connectomes based on physical contact and the corresponding null models. The rows correspond to the different tasks, the columns to the different reservoir configurations. In the individual plots, the model-based estimated means ± 95% CI is plotted against the age of the organism.

	Pearson’s correlation coefficient			RMSE
Connectome	Mean Age	Fav. orig.	Fav. null	Mean Age	Fav. orig.	Fav. null
phys_contact	$-0.20$	$0$	$7$	$+0.044$	$0$	$7$
syn_count	$+0.35$	$7$	$0$	$+0.0065$	$0$	$4$ 1 1 1 Three Age levels non-significant.
syn_size	$+0.24$	$5$	$0$ 2 2 2 Two Age levels non-significant.	$+0.027$	$0$	$5$ 2 2 2 Two Age levels non-significant.

Table 2: Simple contrasts (original

-

Null_{1}

) for age for the Memory Capacity Task. Beta regression with Pearson’s correlation coefficient scores: positive

\Rightarrow

original better. Gamma/Gaussian regression with RMSE scores: positive

\Rightarrow

original worse. 0 0 footnotetext: Note: Counts are Holm-adjusted Age levels with

p<0.05

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Panel of Figure 9 — Figure 9: Plots of the time series data associated with each task.

Explore similar work

The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs
Jun 5, 2026Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-LlorenteMetaheuristic Optimization Reservoir Computing
ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain
Connectome-to-Function: Conditional Generative Latent Representations for Reservoir Computing
Sep 5, 2026Zhuolin Yu, Xingyu Liu, Yuanhao Jia +4Graph Representation Learning Graph Generation
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China · School of Electronics Engineering and Computer Science, Peking University, Beijing, China · School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China +2
A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks
Oct 7, 2026Joonghui Cho, Minchan Kang, Daeshik KimMathematical Reasoning
Korea Advanced Institute of Science and Technology (KAIST)

Jun 5, 2026J/K move · Enter open · S save

The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs

Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-Llorente

ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain

Metaheuristic Optimization Reservoir Computing

Open paper AskPDF arXiv

Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological neural connectomes, shaped by millions of years of evolution, may encode computational structure beyond what random reservoirs provide, yet whether that structure can be further enhanced by principled optimisation remains an open question. We address it by applying four gradient-free, bio-inspired optimisers (Particle Swarm Optimisation, Differential Evolution, Grey Wolf Optimiser, and Whale Optimisation Algorithm) to the edge weights of connectome-based echo-state networks across six species spanning six orders of magnitude in neural complexity: C. elegans (279 neurons), Drosophila (49 nodes), mouse (112), rat (73), macaque (29 regions, continuous FLNe synaptic strengths), and human structural MRI connectivity (83 parcels). Each connectome is evaluated on four canonical reservoir computing benchmarks: Memory Capacity (MC), Lorenz attractor prediction, NARMA-10 system identification, and Mackey-Glass chaotic time-series prediction. All four optimisers consistently outperform unoptimised biological baselines across every task and species when initialised from biological weights. WOA achieves the largest gains on every task: up to a 17x MC improvement (C. elegans: 1.39 to 23.91) and up to 89% NRMSE reduction (Mackey-Glass, human), corresponding to an average 214% improvement across all species and tasks. Crucially, random initialisation on the same topology reliably underperforms biology, establishing biological weight values as an essential inductive bias that topology alone cannot recover. These results position bio-inspired, biologically-initialised optimisation as a principled and broadly effective strategy for connectome reservoir computing across the animal kingdom.

Abstract

Explore similar work

The Whale That Outswam Evolution: Swarm Intelligence Maximises Memory in Connectome Reservoirs

Connectome-to-Function: Conditional Generative Latent Representations for Reservoir Computing

A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks