Neuromorphic Photonics with Coherent Linear Neurons using dual-IQ modulation cells

Neuromorphic photonics aims to transfer the high-bandwidth and low-energy credentials of optics into neuromorphic computing architectures, intending to mimic the architectural principles of brain-inspired computational machines via light-enabled artificial neurons. In this effort, photonic neurons are trying to combine the optical interconnect segments with functional optics that can realize all critical constituent neuromorphic functions, including the linear neuron stage and the activation function. However, complying with the typical requirements of well-established neural network training models for smoothly synergizing the photonic hardware with the best-in-class training algorithms, a linear photonic neuron has to be able to handle both positive and negative weight values, while the activation response has to closely follow widely used mathematical activation functions. Herein, we demonstrate a coherent linear neuron architecture that relies on a dual-IQ modulation cell as its basic neuron element, introducing distinct optical elements for weight amplitude and weight sign representation and exploiting binary optical carrier phase-encoding for positive/negative number representation. We present experimental results of a typical IQ modulator performing as an elementary two-input linear neuron cell and successfully implementing all-optical linear algebraic operations with 100-ps long optical pulses. We also provide the theoretical proof and formulation of how to extend a dual-IQ modulation cell into a complete N-input coherent linear neuron stage that requires only a single-wavelength optical input and avoids the resource-consuming Wavelength Division Multiplexing (WDM) weighting schemes. An 8-input coherent linear neuron is then combined with an experimentally validated optical sigmoid activation function into a physical layer simulation environment, with respective training and physical layer simulation results for the MNIST dataset revealing an average accuracy of 97.24% and 94.37%, respectively.