Photonic Neural Network implementations have been gaining considerable attention as a potentially disruptive future technology. Demonstrating learning in large scale neural networks is essential to establish photonic machine learning substrates as viable information processing systems. Realizing photonic Neural Networks with numerous nonlinear nodes in a fully parallel and efficient learning hardware was lacking so far. We demonstrate a network of up to 2500 diffractively coupled photonic nodes, forming a large scale Recurrent Neural Network. Using a Digital Micro Mirror Device, we realize reinforcement learning. Our scheme is fully parallel, and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges and we achieve very good performance.

Photonic implementations of reservoir computing (RC) have been receiving considerable attention due to their excellent performance, hardware, and energy efficiency as well as their speed. Here, we study a particularly attractive all-optical system using optical information injection into a semiconductor laser with delayed feedback. We connect its injection locking, consistency, and memory properties to the RC performance in a non-linear prediction task. We find that for partial injection locking we achieve a good combination of consistency and memory. Therefore, we are able to provide a physical basis identifying operational parameters suitable for prediction.

Machine learning techniques have proven very efficient in assorted classification tasks. Nevertheless, processing time-dependent high-speed signals can turn into an extremely challenging task, especially when these signals have been nonlinearly distorted. Recently, analogue hardware concepts using nonlinear transient responses have been gaining significant interest for fast information processing. Here, we introduce a simplified photonic reservoir computing scheme for data classification of severely distorted optical communication signals after extended fibre transmission. To this end, we convert the direct bit detection process into a pattern recognition problem. Using an experimental implementation of our photonic reservoir computer, we demonstrate an improvement in bit-error-rate by two orders of magnitude, compared to directly classifying the transmitted signal. This improvement corresponds to an extension of the communication range by over 75%. While we do not yet reach full real-time post-processing at telecom rates, we discuss how future designs might close the gap.

We report on ultrafast artificial laser neurons and on their potentials for future neuromorphic (brain-like) photonic information processing systems. We introduce our recent and ongoing activities demonstrating controllable excitation of spiking signals in optical neurons based upon Vertical-Cavity Surface Emitting Lasers (VCSEL-Neurons). These spiking regimes are analogous to those exhibited by biological neurons, but at sub-nanosecond speeds (>7 orders of magnitude faster). We also describe diverse approaches, based on optical or electronic excitation techniques, for the activation/inhibition of sub-ns spiking signals in VCSEL-Neurons. We report our work demonstrating the communication of spiking patterns between VCSEL-Neurons towards future implementations of optical neuromorphic networks. Furthermore, new findings show that VCSEL-Neurons can perform multiple neuro-inspired spike processing tasks. We experimentally demonstrate photonic spiking memory modules using single and mutually-coupled VCSEL-Neurons. Additionally, the ultrafast emulation of neuronal circuits in the retina using VCSEL-Neuron systems is demonstrated experimentally for the first time to our knowledge. Our results are obtained with off-the-shelf VCSELs operating at the telecom wavelengths of 1310 and 1550 nm. This makes our approach fully compatible with current optical network and data centre technologies; hence offering great potentials for future ultrafast neuromorphic laser-neuron networks for new paradigms in brain-inspired computing and Artificial Intelligence.