On the effect of the thermal cross-talk in a photonic feed-forward neural network based on silicon microresonators

Abstract

Local heating is widely used to trim or tune photonic components in integrated optics. Typically, it is achieved through the power dissipation of metal microwires driven by a current and placed nearby the photonic component. Then, via the thermo-optic effect, both the amplitude and the phase of the complex optical field propagating in the component can be controlled. In the last decade, optical integrated circuits with a cascade of more than 60 thermo-optical phase shifters were demonstrated for quantum simulators or optical neural networks. In this work, we demonstrate a simple two layers feed-forward neural network based on cascaded of thermally controlled Mach-Zehnder interferometers and microring resonators. We show that the dynamics of a high quality factor microresonator integrated into a Silicon On Insulator (SOI) platform is strongly affected by the current flowing in metal heaters where these last generate both local as well as global heating on the integrated photonic circuit. Interestingly, microheaters, even when they are at distances of a few millimetres from the optical component, influence all the microresonators and the Mach-Zehnder interferometers in the photonic circuit. We model the heat flux they generate and modify accordingly the non-linear equations of a system formed by a microresonator coupled to a bus waveguide. Furthermore, we show experimentally that the use of microheaters can be a limiting factor for the feed-forward neural network where three microresonators are used as non-linear nodes. Here, the information encoding, as well as the signal processing, occurs within the photonic circuit via metal heaters. Specifically, the network reproduces a given non-linear surjective function based on a domain of at most two inputs and a co-domain of just one output. As a result, its training aims to determine the values of the currents to apply to the heaters in the hidden layers, which allows replicating a certain shape. We demonstrate how the network exploits mainly the heat flow generated by the information encoding to reproduce a target avoiding the use of all the hidden layer heaters. This work shows that in large thermally actuated integrated photonic circuit, the thermal cross talk is an issue.

Thermal modeling of hybrid three-dimensional integrated, ring-based silicon photonic–electronic transceivers

“…18 Also, for large distances (>200 μm), the thermal crosstalk is quasi-constant, similar to the results reported in Ref. 19. To assess the impact of the flip-chip EIC integration on the PIC, the calibrated FE model is simulated with and without EIC [Fig.…”

Equalization of a 10 Gbps IMDD signal by a small silicon photonics time delayed neural network

“…where ϕ 0 k is the relative phase measured at zero currents, i k is the optimal current in the kth channel, and γ k is the conversion factor between the dissipated thermal power in a resistor and the induced phase shift in the underneath waveguide. Measurements conducted on test resistor structures yield γ k ≈ 0.01 rad∕mA 2 [20], while finding ϕ 0 k is cumbersome due to the uncertainties in the optical path lengths and widths caused by the finite fabrication resolution. Therefore, for the sake of clarity, we show in Fig.…”

Multi-stage spontaneous symmetry breaking of light in Kerr ring resonators

“…Atop these novel field behaviours, the system further provides the option of producing, on a single device, the field behaviours of the two separate systems, counter-propagation and orthogonal polarizations. This is to say, it can produce the behaviours of two counter propagating fields-lending itself to applications such as enhancing the Sangac effect for use in rotation sensors 6 , gyroscopes 16 , and elsewhere, and in the realisation of all-optical components, such as isolators and circulators 27 , while also being able to produce the behaviours of the system with two orthogonal polarisation components, allowing for applications such as acting as a Kerr polarisation controller 23 , potentially supporting (fast-time) temporal cavity solitons for the generation of frequency combs 24,25 , or for use in optical neural networks used in artificial intelligence applications or for systems for quantum information processing 30 . The benefit of this combined system however should be obvious-it can achieve the behaviours of both systems simultaneously, all while taking place within one resonator.…”