No abstract

The inscription of a two-dimensional periodic lattice in the Schott IOG1 phosphate glass, by employing a laser assisted selective chemical etching method, is presented here. A two step patterning approach is employed, wherein damage is induced into the glass volume by exposure to intense laser radiation and subsequently, a chemical development in an alkali solution, selectively etches the exposed areas. A simple four beam interferometric setup is used for defining the two-dimensional periodic pattern on the sample surface. The exposures were performed by using the output of a high coherence 213nm, 150ps Nd:YAG laser; while the chemical developing was carried out in aqueous KOH solution. The periodic structures inscribed have periodicities of the order of 500nm and depth greater than 200nm. These Bragg reflectors are characterized by means of diffraction efficiency, and surface topology by employing atomic force and scanning electron microscopy. Issues related with the interferometric and wet etching processes are also presented and discussed.

Analog photonic computing comprises a promising candidate for accelerating the linear operations of deep neural networks (DNNs), since it provides ultrahigh bandwidth, low footprint and low power consumption computing capabilities. However, the confined photonic hardware size, along with the limited bit precision of high-speed electro-optical components, impose stringent requirements towards surpassing the performance levels of current digital processors. Herein, we propose and experimentally demonstrate a speed-optimized dynamic precision neural network (NN) inference via tiled matrix multiplication (TMM) on a low-radix silicon photonic processor. We introduce a theoretical model that relates the noise figure of a photonic neuron with the bit precision requirements per neural layer. The inference evaluation of an NN trained for the classification of the IRIS dataset is, then, experimentally performed over a silicon coherent photonic neuron that can support optical TMM up to 50 GHz, allowing, simultaneously, for dynamic-precision calculations. Targeting on a high-accuracy and speed-optimized classification performance, we experimentally applied the model-extracted mixed-precision NN inference scheme via the respective alteration of the operational compute rates per neural layer. This dynamic-precision NN inference revealed a 55% decrease in the execution time of the linear operations compared to a fixed-precision scheme, without degrading its accuracy.

Non-von-Neumann computing architectures and Deep Learning training models have sparked a new computational era where neurons are forming the main architectural backbone and vector, matrix and tensor multiplications comprise the basic mathematical toolbox. This paradigm shift has triggered a new race among hardware technology candidates; within this frame, the field of neuromorphic photonics promises to convolve the targeted algebraic portfolio along a computational circuitry with unique speed, parallelization, and energy efficiency advantages. Fueled by the inherent energy efficient analog matrix multiply operations of optics, the staggering advances of photonic integration and the enhanced multiplexing degrees offered by light, neuromorphic photonics has stamped the resurgence of optical computing brining a unique perspective in low-energy and ultra-fast linear algebra functions. However, the field of neuromorphic photonics has relied so far on two basic architectural schemes, i.e., coherent linear optical circuits and incoherent WDM approaches, where wavelengths have still not been exploited as a new mathematical dimension. In this paper, we present a radically new approach for promoting the synergy of WDM with universal linear optics and demonstrate a new, high-fidelity crossbar-based neuromorphic photonic platform, able to support matmul with multidimensional operands. Going a step further, we introduce the concept of programmable input and weight banks, supporting in situ reconfigurability, forming in this way the first WDM-equipped universal linear optical operator and demonstrating different operational modes like matrix-by-matrix and vector-by-tensor multiplication. The benefits of our platform are highlighted in a Fully Convolutional Neural Network layout that is responsible for parity identification in the MNIST handwritten digit dataset, with physical layer simulations revealing an accuracy of ~94%, degraded by only 2% compared to respective results obtained when executed entirely by software. Finally, our in-depth analysis provides the guidelines for neuromorphic photonic processor performance improvement, revealing along the way that 4-bit quantization is sufficient for inputs, whereas the weights can be implemented with as low as 2-bits of precision, offering substantial benefits in terms of driving circuitry complexity and energy savings.

No abstract