ARIADNE · Artificial intelligence enabled by automatic dynamic exploration of integrated photonic spiking neural networks
Horizon Europe — Marie Skłodowska-Curie Actions
- Duration
- 2023-04-01 → 2025-03-31
- EU contribution
- €188,590
- Participants
- 1
- Scheme
- HORIZON-TMA-MSCA-PF-EF
Lines connect the coordinator with its partners.
Results in brief
Artificial intelligence enabled by automatic dynamic exploration of integrated photonic spiking neural networks
Machine learning (ML) and artificial intelligence (AI) have shown incredible usefulness across science and technology, transforming markets and society. However, their increasing adoption and development come with significant energy costs, which undermines their sustainability. What's more, their current applications barely scratch the surface of their full potential. One way to boost AI's energy efficiency, speed, and overall sustainability and applicability is to host ML models on dedicated, non-digital hardware, like hardware neural networks with physical artificial neurons and connections, instead of simulating them on conventional digital computers. For example, processing optical data (like the internet data carried by light in fiber optics) with a photonic neural network keeps the processing in the optical domain. This avoids the energy consumption, latency, and information loss that happen when data is converted and digitized. Relevant examples of optical data include telecom signals through optical fibers and signals from numerous optical sensing applications, such as for biomedical or environmental monitoring. However, while photonic circuits are generally great for efficient linear operations and data transfer, they face challenges in performing the nonlinear operations and long-term memory tasks crucial for many neural network and ML implementations. ARIADNE has developed ML applications using a new type of on-chip photonic neural network. This network leverages highly complex optical dynamics within a system of microresonators. This system allows us to process optical data for ML, including both nonlinear operations and long-term memory, in a fast and energy-efficient way and it finds application in enhancing a wide variety of optics-based technologies.
Data: CORDIS, © European Union
Project objective
In this project (ARIADNE) I will address several key challenges of today’s hardware-based neuromorphic computing by developing a novel AI system based on a highly complex, dynamical and nonlinear integrated photonic neural network that is easy to fabricate and consumes low power. The proposed implementation is enabled by an original machine learning approach which allows to considerably relax the requirements on fabrication reproducibility and on observability and tunability of the network parameters. The AI system is expected to learn to perform multiple complex and time-dependent computational tasks at high speed within a compact device, finding application in real-time control with enhanced cybersecurity (robotics, autonomous vehicles, internet of things, …) and physiological signals analysis (e.g. prediction of epileptic seizures). ARIADNE will be hosted by the NanoLab research group at the University of Trento (UNITN).The project acronym is inspired by the ancient Greek myth of Theseus and the Minotaur, where princess Ariadne comes up with an ingenious way to help Theseus escape the labyrinth. In ARIADNE I aim to let a reinforcement learning algorithm learn to solve, loosely speaking, the spatio-temporal maze represented by the complicated dynamics in the considered networks of integrated optical resonators. In particular, the reinforcement learning algorithm will learn to control a complex feedback loop in order to set favorable dynamical network properties that allow to carry out target computational tasks.The AI system is expected to learn to perform multiple complex and time-dependent computational tasks at high speed within a compact device, finding application in real-time control with enhanced cybersecurity (robotics, autonomous vehicles, internet of things, …) and physiological signals analysis (e.g. prediction of epileptic seizures).
Original text from CORDIS.
Participants
- UNIVERSITA DEGLI STUDI DI TRENTO · TrentoCoordinatorItaly
Links
- View on CORDIS
- DOI: 10.3030/101064322
- https://ec.europa.eu/research/participants/documents/downloadPublic?documentIds=080166e5021bf90a&appId=PPGMS
- https://ec.europa.eu/research/participants/documents/downloadPublic?documentIds=080166e519551624&appId=PPGMS
Data: CORDIS, © European Union