PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Software-implementation of brain-inspired computing approaches underlie many important modern-day computational tasks. Yet, traditional computing architectures physically separate the core computing functions of memory and processing. I will present an all-optical approach to overcome these restrictions by developing photonic spiking neurons interconnected via an integrated photonics network to photonic synapses. I will present our results in scaling to multi-element circuits and report on their optical performance in pattern recognition and data storage. Photonic implementations give access to the speed, bandwidth and power improvements inherent to optical systems, which will be attractive for the direct processing of data in the optical domain.
Wolfram H. P. Pernice
"Artificial photonic neural networks (Conference Presentation)", Proc. SPIE 11284, Smart Photonic and Optoelectronic Integrated Circuits XXII, 1128409 (9 March 2020); https://doi.org/10.1117/12.2545601
ACCESS THE FULL ARTICLE
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Wolfram H. P. Pernice, "Artificial photonic neural networks (Conference Presentation)," Proc. SPIE 11284, Smart Photonic and Optoelectronic Integrated Circuits XXII, 1128409 (9 March 2020); https://doi.org/10.1117/12.2545601