This work compares 7,560 reservoir designs, all combinations of six design factors, each built as many random reservoirs, on recalling the majority or the parity of a few input bits seen several steps earlier, to study random Boolean networks as reservoirs.
Christopher Michael Skeide Vibe, Aliaksandr Hubin, Stefano Nichele· 0 citations
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 and 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.
F. Reimers, O. H. Ramstad, Aliaksandr Hubin et al.· 0 citations
Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and memorization in few-shot regimes. Neural Cellular Automata (NCAs) offer a highly parameter-efficient alternative, yet research has focused primarily on their output, leavin...
We study an in silico substrate in which every pixel of a two-channel cellular-automata grid carries a tiny neural network (an agent) that senses its Moore neighbourhood. A cell persists only by self-replication: a living neighbour is cloned, and its weights are mutated by a uniform perturbation, so that phenotype (cel...
S. Jain, F. Reimers, Stefano Nichele· Journal of Imaging· 0 citations
This paper investigates the hypothesis that a biologically inspired micro-sleep paradigm, napping -- combining proportional weight scaling with continuous stochastic membrane activity -- can replicate the stability of normalization while shedding model complexity.
A. Massey, Stefano Nichele, Aliaksandr Hubin· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.