Boosting reservoir computing with brain-inspired adaptive control of E-I balance

Keshav Srinivasan, Dietmar Plenz and Michelle Girvan ()
Additional contact information
Keshav Srinivasan: National Institute of Mental Health, Section on Critical Brain Dynamics
Dietmar Plenz: National Institute of Mental Health, Section on Critical Brain Dynamics
Michelle Girvan: University of Maryland, Biophysics Program

Nature Communications, 2025, vol. 16, issue 1, 1-12

Abstract: Abstract Reservoir computers (RCs) are a class of recurrent neural networks that incorporate brain-inspired principles and provide an efficient alternative to deep learning. With fixed random internal connections and trained output weights, they simplify learning but remain sensitive to hyperparameters governing activation and connectivity. While various hyperparameters are commonly tuned, the relative balance between excitatory and inhibitory (E-I) signals—fundamental to brain function—is typically fixed in RCs. Here, we investigate tuning this balance and show that strong performance consistently arises in balanced or slightly over-inhibited regimes, not excitation-dominated ones. Further, we introduce a self-adapting mechanism that locally adjusts E-I balance to achieve target firing rates, reducing hyperparameter tuning costs and yielding up to 130% performance gains in memory capacity and time-series prediction. Incorporating heterogeneity in firing-rate targets further enhances robustness. These findings highlight dynamic adaptation as a promising design principle, improving RC performance while offering insights into neural computation.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64978-8 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64978-8

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64978-8

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().