Dr Rakesh Sengupta, Assistant Professor, Psychology, SIAS recently published a paper titled, Modular Quantum Recurrent Neural Networks: Scalable Reservoir Computing with High Noise Resilience at the 2026 Fourth International Conference on Secure Cyber Computing and Communications (ICSCCC) held in Jalandhar, India.
This research addresses a critical challenge in the field of quantum machine learning: scaling up quantum networks while dealing with the hardware constraints of today’s Noisy Intermediate-Scale Quantum (NISQ) devices.
Key highlights from the publication include:
The introduction of a novel modular architecture that reduces simulation memory by up to 341x for 8-qubit systems.
The discovery of a “noise compartmentalization effect” that effectively shields quantum reservoirs from global decoherence.
Demonstrating that these advanced models are computationally feasible on current quantum hardware, requiring only 896 CNOTs at 8 qubits.
