Chalcogenide phase-change devices for neuromorphic photonic computing

The integration of artificial intelligence systems into daily applications like speech recognition and autonomous driving rapidly increases theamount of data generated and processed. However, satisfying the hardware requirements with the conventional von Neumann architectureremains challenging due to the von Neumann bottleneck. Therefore, new architectures inspired by the working principles of the humanbrain are developed, and they are called neuromorphic computing. The key principles of neuromorphic computing are in-memory comput-ing to reduce data shuffling and parallelization to decrease computation time. One promising framework for neuromorphic computing isphase-change photonics. By switching to the optical domain, parallelization is inherently possible by wavelength division multiplexing, andhigh modulation speeds can be deployed. Non-volatile phase-change materials are used to perform multiplications and non-linearoperations in an energetically efficient manner. Here, we present two prototypes of neuromorphic photonic computation units based onchalcogenide phase-change materials. First is a neuromorphic hardware accelerator designed to carry out matrix vector multiplication inconvolutional neural networks. Due to the neuromorphic architecture, this prototype can already operate at tera-multiply-accumulate persecond speeds. Second is an all-optical spiking neuron, which can serve as a building block for large-scale artificial neural networks. Here,the whole computation is carried out in the optical domain, and the device only needs an electrical interface for data input and readou