Manuylovich and colleagues propose the use of stochastic resonances in neural networks as dynamic nonlinear nodes. They demonstrate the possibility of reducing the number of neurons for a given prediction accuracy and observe that the performance of such neural networks can be more robust against the impact of noise in the training data compared to the conventional networks.
- Egor Manuylovich
- Diego Argüello Ron
- Sergei K. Turitsyn
