In this project, we employ mixed-mode neuromorphic architectures to implement in-memory learning through electrically programmable artificial neurons and synapses based on phase-change materials. Optimal compositions will be devised, implemented, and tested using advanced fabrication methods and nanoscale analytics. We will develop and implement mixed-precision algorithms for in-memory learning and will apply our architecture for processing of external sensory input. In the long term, we strive to develop brain-inspired nanoscale computing devices, which are able to carry out adaptive optical information processing.
| Pernice, Wolfram | |
| Salinga, Martin |
| Pernice, Wolfram | |
| Salinga, Martin |
Duration: 01/01/2021 - 31/12/2024 | 1st Funding period Funded by: DFG - Collaborative Research Centre Type of project: Subproject in DFG-joint project hosted at University of Münster |
Duration: 01/01/2025 - 31/12/2028 | 2nd Funding period Funded by: DFG - Collaborative Research Centre Type of project: Main DFG-project hosted at University of Münster |