Spiking neural networks for streaming qubit readout

2026-10-01

AI Summary

This study addresses the limitations of conventional matched filtering in superconducting qubit readout, which struggles with crosstalk and transient noise while lacking real-time streaming estimation capabilities. To overcome these challenges, this work proposes a chunked streaming quantum state classification method based on spiking neural networks (SNNs). By leveraging quantization-aware training (QAT) and HLS4ML synthesis techniques, the model is efficiently deployed on an FPGA platform to enable low-latency hardware inference. Experimental results demonstrate that a single inference completes before the arrival of the subsequent data chunk, providing dynamically evolving state estimates with high accuracy that approach those of full-trajectory artificial neural networks (ANNs). This work establishes the potential of SNNs for real-time quantum control and scientific inference applications.

Abstract

Fast and accurate qubit-state assignment is essential for feedback, calibration, and error correction in quantum processors. In superconducting platforms, frequency-multiplexed readout makes this task intrinsically multivariate as measured traces can encode crosstalk, qubit-state relaxation events, and other transient nonidealities that are not fully captured by conventional matched filtering. Here, we introduce spiking neural network (SNN) discriminators for superconducting qubit readout. By processing the measurement window in successive time chunks, the networks exploit temporal structure and update classification scores as data arrive, rather than waiting until the end of the readout window. The spiking networks outperform matched-filter discrimination and approach the accuracy of a full-trace artificial neural network. Beyond reaching the performance of artificial neural networks, the key advantage of SNNs is that they provide a streaming, time-resolved estimate of the qubit state that evolves as the readout signal is acquired. Using quantisation-aware training and hls4ml synthesis, we further demonstrate that each FPGA inference update can be completed before the next readout chunk arrives. These results establish spiking neural networks as a promising route to low-latency, real-time qubit readout on FPGA hardware, with broader implications for time-critical quantum-control and scientific-inference applications.

Problem

• qubit readout
• spiking neural networks
• superconducting qubits
• matched filtering
• low-latency

Innovation

• Spiking Neural Networks
• Qubit Readout
• FPGA
• Streaming Inference
• Quantisation-aware Training