Preprint
Sep 2026
Experimental evidence of generalization in quantum machine learning in small-data regime
This work develops a hardware-compatible QCNN with mid-circuit measurement and classical feed-forward, and shows on a binary handwritten-digit task that strong test performance is achievable from as few as 10 training samples, with the generalization error decreasing as the training set grows.
Leena Anthony, Artemiy Burov, N. Piro et al.
· 0 citations