Training of Physical Neural Networks

no code implementations • 5 Jun 2024 • Ali Momeni, Babak Rahmani, Benjamin Scellier, Logan G. Wright, Peter L. McMahon, Clara C. Wanjura, Yuhang Li, Anas Skalli, Natalia G. Berloff, Tatsuhiro Onodera, Ilker Oguz, Francesco Morichetti, Philipp del Hougne, Manuel Le Gallo, Abu Sebastian, Azalia Mirhoseini, Cheng Zhang, Danijela Marković, Daniel Brunner, Christophe Moser, Sylvain Gigan, Florian Marquardt, Aydogan Ozcan, Julie Grollier, Andrea J. Liu, Demetri Psaltis, Andrea Alù, Romain Fleury

Research over the past few years has shown that the answer to all these questions is likely "yes, with enough research": PNNs could one day radically change what is possible and practical for AI systems.

Backpropagation-free Training of Deep Physical Neural Networks

no code implementations • 20 Apr 2023 • Ali Momeni, Babak Rahmani, Matthieu Mallejac, Philipp del Hougne, Romain Fleury

Recent years have witnessed the outstanding success of deep learning in various fields such as vision and natural language processing.

Image Classification

Wave-based extreme deep learning based on non-linear time-Floquet entanglement

no code implementations • 19 Jul 2021 • Ali Momeni, Romain Fleury

Wave-based analog signal processing holds the promise of extremely fast, on-the-fly, power-efficient data processing, occurring as a wave propagates through an artificially engineered medium.

Edge Detection Time Series +1

Reciprocal Metasurfaces for On-axis Reflective Optical Computing

no code implementations • 22 Dec 2020 • Ali Momeni, Hamid Rajabalipanah, Mahdi Rahmanzadeh, Ali Abdolali, Karim Achouri, Viktar Asadchyk, Romain Fleury

Analog computing has emerged as a promising candidate for real-time and parallel continuous data processing.

Optics Applied Physics