AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Recurrent Quantum Neural Networks

Johannes Bausch

NeurIPS 2020 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use UMAP rather than PCA plus t-SNE preprocessingQRNN on full MNIST · Full MNISTAccuracy [%]: $94.6\pm0.4$ -> $96.7\pm0.2$Improved
Ensemble 3 UMAP-preprocessed QRNNsQRNN on full MNIST · Full MNISTAccuracy [%]: $96.7\pm0.2$ -> $\mathbf{99.23\pm0.05}$Improved
Ensemble 4 QRNNsQRNN on MNIST {0, 1} · MNIST {0, 1}Accuracy [%]: $99.2\pm0.2$ -> $\mathbf{99.6\pm0.16}$Improved
Use a 10-qubit L-BFGS QRNN rather than a 12-qubit Adam QRNNQRNN on MNIST {3, 6} · MNIST {3, 6}Accuracy [%]: $89.7\pm 0.8$ -> $97.1\pm0.7$Improved
Ensemble 6 QRNNsQRNN on MNIST {3, 6} · MNIST {3, 6}Accuracy [%]: $97.1\pm0.7$ -> $\mathbf{99.0\pm0.3}$Improved
Use UMAP preprocessing rather than pixel-by-pixel inputsQRNN on full MNIST · Full MNISTAccuracy [%]: $96.7\pm0.2$ vs. $94.6\pm0.4$Improved
Use UMAP instead of t-SNE as the dimensionality reduction methodQRNN preprocessing for MNIST · Full MNISTAccuracy [%]Improved
Use Adam rather than L-BFGS for general QRNN trainingQRNN · Sequence learning tasksConvergence reliabilityImproved
Use a neuron order of 2 rather than other tested orders (ablation)QRNN sentence-learning topology · Sentence structure learningTraining steps to convergenceImproved
Use degree 2 rather than degree 3 or 4 neurons (ablation)QRNN sentence-learning topology · Sentence structure learningTraining steps to convergenceImproved
Use two work stages rather than one (ablation)QRNN sentence-learning topology · Sentence structure learningTraining steps to convergenceImproved
Increase work stages beyond two (ablation)QRNN sentence-learning topology · Sentence structure learningTraining steps to convergenceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy