Hierarchical Serpentine-like Organic Crystal Optical Waveguides for Artificial Neural Networks

TL;DR

This paper demonstrates a novel four-layered organic optical neural network architecture using flexible crystal waveguides, enabling parallel optical signal transmission and mimicking neural network functions.

Contribution

It introduces a hierarchical, serpentine-like organic crystal waveguide system for optical neural networks, constructed via mechanical micromanipulation, with integrated optical synapses for signal processing.

Findings

Successful fabrication of a four-layered organic optical neural network

Demonstration of parallel optical signal transmission through synapses

Hierarchical architecture mimics neural network signal processing

Abstract

Optical components and circuits that deal with multiple signal generation and processing are quintessential for artificial neural networks. Herein, we present a proof-of-concept four-layered organic optical artificial neural network (ANN)-like architecture, constructed from flexible organic crystals of (E)-1-(((5-methylpyridin-2-yl)imino)methyl)naphthalene-2-ol (MPyIN), employing an atomic force microscopy cantilever tip-based mechanical micromanipulation technique. Initially, the strategic selection of four MPyIN crystal active waveguides of varying lengths, mechanically bending them into serpentine-like forms, followed by their hierarchical integration, creates neuron-like, four-layered interconnected optical waveguides with six optical synapses. The synapses in the ANN-like architecture enable parallel transmissions of passive optical signals via evanescent coupling across multiple paths through various layers of the serpentine-shaped optical waveguides. Notably, the feedforward mechanism allows the synapses to multiply and split the optical signal generated at any input into four diverging signals with varying magnitudes. Here, certain outputs deliver a mixed signal (passive and active) due to diverging and converging optical transmission paths. This hierarchical, ANN-like tiny architecture paves the way for the development of smart optical neural networks utilizing multiple emissive and phase-changing organic crystals.