Become A Wiser, More Profitable Trader

✅   Brain-inspired interpretable reservoir computing with resonant recurrent neural networks

science

:2506.17083v1 Announce Type: new Abstract: Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of biological neurons, we describe a reservoir computing framework with explicit damped, oscillatory node dynamics. We express the oscillatory dynamics using two history dependent terms to connect these dynamics with existing artificial neural network approaches and apply physical and stationary constraints to reduce the number of free parameters. We then optimize and illustrate reservoir performance by classifying different brain rhythms associated with epilepsy and show that reservoir elements support classification by resonating with features of the input signals.

arXiv     Jun 23, 2025