Low-Loss Photonic Reservoir Computing with Multimode Photonic Integrated Circuits

Abstract

We present a numerical study of a passive integrated photonics reservoir computing platform based on multimodal Y-junctions. We propose a novel design of this junction where the level of adiabaticity is carefully tailored to capture the radiation loss in higher-order modes, while at the same time providing additional mode mixing that increases the richness of the reservoir dynamics. With this design, we report an overall average combination efficiency of 61% compared to the standard 50% for the single-mode case. We demonstrate that with this design, much more power is able to reach the distant nodes of the reservoir, leading to increased scaling prospects. We use the example of a header recognition task to confirm that such a reservoir can be used for bit-level processing tasks. The design itself is CMOS-compatible and can be fabricated through the known standard fabrication procedures.

Tutorial: Photonic neural networks in delay systems

“…Finally, explorations beyond the single delay node photonic RC architecture are of pressing importance. These include investigation of multi-node Reservoirs 98 , implementations into large scale spatio-temporal networks 64 and into integrated photonic chips [99][100][101] .…”

Riding Waves in Neuromorphic Computing

“…This approach makes the optimization more efficient than regular architectures, yet the network retains the requirements for learning complexity. Proposed designs for RC neuromorphic devices involve optoelectronic technology [6], photonic cavities [7], and photonic integrated circuits [8].…”

Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation

“…Photonic implementations tap into high bandwidth and versatile platforms, ranging from free-space optics to fiber-based systems and integrated optical circuits. Different flavors of electronic, opto-electronic and all-optical reservoirs exist, including delay-based systems [4][5][6][7][8][9][10][11][12], network-based systems [13][14][15][16][17] and speckle-based systems [18][19][20][21]; an overview is given in [22]. Noise and parameter variations can affect a reservoir's performance in different ways, as was investigated, for example, in [23][24][25].…”