Few-molecule reservoir computing is an emerging paradigm in nanoscale information processing that harnesses the complex dynamics of small ensembles of molecules to perform computational tasks. By ...
Scientists have developed a new kind of laser-based artificial neuron that mimics a biological nerve cell. This artificial ...
Reservoir computing is said to be improved by reducing the amount of computation needed; it is faster and more computationally efficient. The innovation is said to be inspired by how the brain works.
More information: Daiki Nishioka et al, Few- and single-molecule reservoir computing experimentally demonstrated with surface-enhanced Raman scattering and ion gating, Science Advances (2024). DOI ...
They showed that conventional reservoir computing (RC), a type of RNN, can be viewed as a linear approximation, and introduced a 'generalized readout' incorporating further order approximations.
The technology demonstrated significantly higher information processing performance than conventional physical reservoir computing devices, underscoring its potential to transform AI technologies.