SQC Quantum Reservoir Delivers Deep Learning Performance With Reduced Training Time and Hardware Demands
October 13 2025 -- Telstra and Silicon Quantum Computing (SQC) today announced results from a joint initiative taking quantum computing out of the lab and into the telecommunications industry – marking a new milestone in Australia’s journey towards quantum-enabled digital infrastructure.
Over 12 months a Telstra-SQC team explored how quantum machine learning could enhance Telstra’s response to a complex challenge in connectivity: predictive analytics.
Advances in predictive network analytics have the potential to reshape customer experiences, from pre-empting and resolving network issues, to powering personalised services like dynamic bandwidth upgrades responding to real-time demand.
Today, Telstra uses a combination of machine learning and AI to help predict network performance and detect changes in network patterns. These systems analyse metrics like latency and bandwidth to predict potential variances.
This enables Telstra to proactively monitor and reconfigure network resources, deploy technicians or initiate automated responses - often before customers are impacted.
SQC’s quantum experts and Telstra engineers tested and evaluated SQC’s quantum-enhanced machine learning system called Watermelon, a quantum reservoir that generates quantum features that can be used in an AI model.
The goal was twofold - first, to assess if features generated by the quantum reservoir could be used to forecast network metrics, and second, to compare the performance against a recently developed deep learning model.
The results were significant. Training and fine-tuning the quantum reservoir took just days, delivering accuracy on par with a deep learning model that required weeks of effort.
Put simply, the quantum-enhanced model matched the performance of Telstra’s current model - but was trained much faster.
The reservoir also operated efficiently without the GPU hardware demands of the deep learning model. As cutting-edge AI can be resource intensive, technologies that reduce its cost are increasingly valuable.
Shailin Sehgal, Telstra's Group Executive of Global Networks and Technology, said that combining Telstra’s experience in managing complex connectivity with SQC’s world-class quantum systems - proved that pairing deep domain knowledge with cutting-edge engineering can lead to innovation with potential real-world customer impact.
Michelle Simmons, CEO of Silicon Quantum Computing, said the results were a glimpse into the future, from quicker insights leading to real-world customer outcomes and reduced computational overhead.
The program lays the foundation for broader investigation of quantum technology in digital infrastructure and real-world industry applications.