Daniel Brunner

Neural network inspired computational architectures have been inspired by the physical structure of the human brain. There, a large number of nonlinear nodes are connected inside a large scale network, and learning is generally interpreted via modifications to the networks connectivity structure. Yet, implementations of neural networks are typically based on their emulation within serial and binary logic computers. Recently, Reservoir Computing (RC) has been demonstrated with various levels of hardware implementations inside nonlinear networks implemented in a delay system. I will demonstrate how the same scheme can be realized in a photonic networks of 1600 nonlinear oscillators. Furthermore, I will report on first results of a full implementation of hardware-based learning. Our system therefore presents a large step to a full physical implementation of the originally envisioned neuromorphic computing systems.