PELM: Photonic Extreme Learning Machine: from neuromorphic computing to universal optical interpolant, strain gauge sensor and cancer morphodynamic monitor.
The PELM project aims at demonstrating machine learning photonic devices. Within a single neuromorphic computing architecture, different platforms are specialized to given tasks by their specific characteristics. Starting from a common theoretical algorithm where matrices of optical computational nodes constitute a neural network, innovative proof-of-concept prototypes are realized such as:
- Silicon integrated sequence of optical micro-ring resonators for photonic neuromorphic computing;
- Semiconductor nanowire metasurfaces for arbitrary optical function synthesis suitable for flat lenses in computer tablet or smartphone applications;
- Liquid polymeric droplet whispering gallery mode resonator for sensitive strain gauge sensing;
- Biological spherical resonators for cancer detection and morphodynamics monitoring.
The unique combination of skilled physicists, engineers and biologists- from both universities and research centers- guarantees the achievement of these ambitious goals. Complementary competences in photonic integrated devices, complex systems, linear and nonlinear optical measurements, bio-physics, and semiconductor technology allow developing various platforms for the photonic extreme learning machines and their validation on killer applications.