Back

Reservoir Computing with Ultra-Sparse Rings

Talidou, A.; Nicola, W.

2026-02-23 neuroscience
10.64898/2026.02.21.707238 bioRxiv
Show abstract

Many existing models of computation in recurrent neural networks assume dense, unconstrained initial connectivity, where any pair of neurons may be coupled to generate the rich dynamics needed for learning complex temporal patterns. Inspired by invertebrate circuits that often exhibit ring-like connectivity, we show that computation can occur in ultra-sparse spiking and rate reservoirs that are initially coupled as simple unidirectional rings. In contrast to standard recurrent networks, the total number of network parameters in these ring networks scales only linearly with network size, while still producing rich feature sets. We demonstrate that such networks can successfully reproduce a range of dynamical systems tasks, including oscillations, multi-stable switches, and low-dimensional chaotic attractors. Our findings show that structured spatio-temporal dynamics naturally arising from large ring topologies, often observed in invertebrate circuits, are a sufficient mechanism for learning different types of attractors.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
PLOS Computational Biology
1633 papers in training set
Top 1%
17.2%
2
Frontiers in Computational Neuroscience
53 papers in training set
Top 0.2%
9.9%
3
Neural Computation
36 papers in training set
Top 0.1%
9.0%
4
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 8%
8.2%
5
Nature Communications
4913 papers in training set
Top 25%
7.0%
50% of probability mass above
6
Scientific Reports
3102 papers in training set
Top 15%
6.7%
7
PLOS ONE
4510 papers in training set
Top 35%
4.2%
8
Neuron
282 papers in training set
Top 4%
3.0%
9
Cell Reports
1338 papers in training set
Top 18%
2.7%
10
Physical Review E
95 papers in training set
Top 0.6%
1.8%
11
Neural Networks
32 papers in training set
Top 0.4%
1.7%
12
eneuro
389 papers in training set
Top 6%
1.7%
13
Bulletin of Mathematical Biology
84 papers in training set
Top 1%
1.5%
14
Biological Cybernetics
12 papers in training set
Top 0.1%
1.3%
15
eLife
5422 papers in training set
Top 48%
1.3%
16
Journal of Computational Neuroscience
23 papers in training set
Top 0.3%
1.2%
17
Nature Neuroscience
216 papers in training set
Top 5%
0.9%
18
Communications Biology
886 papers in training set
Top 19%
0.9%
19
Physical Review X
23 papers in training set
Top 0.5%
0.9%
20
Journal of The Royal Society Interface
189 papers in training set
Top 4%
0.9%
21
iScience
1063 papers in training set
Top 34%
0.7%
22
Science Advances
1098 papers in training set
Top 30%
0.7%
23
Science
429 papers in training set
Top 20%
0.7%
24
PRX Life
34 papers in training set
Top 1%
0.7%
25
Cell Systems
167 papers in training set
Top 13%
0.7%
26
Neurocomputing
13 papers in training set
Top 0.7%
0.6%
27
Physical Review Research
46 papers in training set
Top 1%
0.6%