Isolating Quantum Inductive Bias: A Twin-Architecture Benchmark for Data-Scarce Medical Imaging
Conference paper · TQCEBT 2026
The question in plain language
When medical imaging data is scarce, what does a quantum component contribute to a learning system? The paper’s twin-architecture benchmark frames this question around quantum inductive bias: how a model’s structure shapes what it can learn from limited examples.
The full experimental setup, comparisons and findings are in the linked paper on IEEE Xplore.
Presentation record
The recorded presentation is associated with TQCEBT 2026, held 9–11 April 2026, paper identifier TQCEBT26-PP0961. It is distinct from the NIT federated-learning manuscripts.
Availability
Read the paper on IEEE Xplore for the full study and publication record. The conference presentation and this paper belong to the quantum-inductive-bias research direction; the NIT federated-learning manuscripts are separate work.
Isolating Quantum Inductive Bias: A Twin-Architecture Benchmark for Data-Scarce Medical Imaging. TQCEBT 2026. IEEE Xplore: https://ieeexplore.ieee.org/document/11681822