All-Optical Reinforcement Learning In Solitonic X-Junctions
| Autor: | Alessandro Belardini, Eugenio Fazio, D. Moscatelli, M. Alonzo, L. Bastiani, Cesare Soci |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Computer science
Decision Making Spatial Learning lcsh:Medicine 02 engineering and technology Topology 01 natural sciences Article Pheromones 010309 optics Simple (abstract algebra) 0103 physical sciences Reinforcement learning Animals lcsh:Science Reinforcement Feedback Physiological Multidisciplinary Behavior Animal Ants lcsh:R Nonlinear optics Ant colony 021001 nanoscience & nanotechnology Path (graph theory) Pheromone lcsh:Q 0210 nano-technology Reinforcement Psychology |
| Zdroj: | Scientific Reports Scientific Reports, Vol 8, Iss 1, Pp 1-7 (2018) |
| ISSN: | 2045-2322 |
| Popis: | Ethology has shown that animal groups or colonies can perform complex calculation distributing simple decision-making processes to the group members. For example ant colonies can optimize the trajectories towards the food by performing both a reinforcement (or a cancellation) of the pheromone traces and a switch from one path to another with stronger pheromone. Such ant’s processes can be implemented in a photonic hardware to reproduce stigmergic signal processing. We present innovative, completely integrated X-junctions realized using solitonic waveguides which can provide both ant’s decision-making processes. The proposed X-junctions can switch from symmetric (50/50) to asymmetric behaviors (80/20) using optical feedbacks, vanishing unused output channels or reinforcing the used ones. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|