A 20.0% increase in training loss efficiency (0.42/0.35), and a 14.9% increase in validation loss efficiency (0.54/0.47) was experienced using two QML algorithms in parallel vs. a single QML algorithm with the Bromley, T. Torch layers demo. (Slide 15) Efficiency Metrics Single QML Algorithms vs. Parallel QML Algorithms 1-11-24.pdf - Google Drive
!