Research map / Architectures and efficiency / RNNs and normalization
What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement.
Yotam Alexander, Nimrod De La Vega, Noam Razin, Nadav Cohen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Rearrange randomly permuted features with the entanglement-based algorithm | CNN · Speech Commands (randomly permuted) | test accuracy: 5.5 -> 18 | Improved |
| Rearrange randomly permuted features with the entanglement-based algorithm | S4 · Speech Commands (randomly permuted) | test accuracy: 9.4 -> 30.1 | Improved |
| Rearrange randomly permuted features with the entanglement-based algorithm | Local-Attention · Speech Commands (randomly permuted) | test accuracy: 7.8 -> 12.9 | Improved |
| Rearrange features with IGTD instead of random permutation | CNN · Speech Commands (randomly permuted) | test accuracy: 5.5 -> 5.7 | No clear effect |
| Rearrange features with IGTD instead of random permutation | S4 · Speech Commands (randomly permuted) | test accuracy: 9.4 -> 12.8 | Improved |
| Use entanglement-based arrangement instead of IGTD | S4 · dna | test accuracy: 89.9 -> 89.1 | Hurt |
| Rearrange tabular features with the entanglement-based algorithm | CNN · dna | test accuracy: 82.5 -> 91.2 | Improved |
| Rearrange tabular features with the entanglement-based algorithm | Local-Attention · semeion | test accuracy: 60.9 -> 78.0 | Improved |
| Rearrange tabular features with the entanglement-based algorithm | S4 · isolet | test accuracy: 92.3 -> 93.4 | Improved |
| Rearrange tabular features with the entanglement-based algorithm | CNN · semeion | test accuracy: 77.7 -> 80.0 | Improved |
| Increase number of random feature swaps in audio data | CNN, S4, Local-Attention · Speech Commands binary | entanglement and test accuracy | Hurt |
| Rearranged features vs original arrangement on Speech Commands | CNN · Speech Commands | test accuracy: 59.8 -> 18 | Hurt |
Closest papers by meaning
- Exponential Hardness of Optimization from the Locality in Quantum Neural Networks (AAAI 2024 · similarity 0.85)
- Exponential Quantum Communication Advantage in Distributed Inference and Learning (NeurIPS 2024 · similarity 0.83)
- Exploring channel distinguishability in local neighborhoods of the model space in quantum neural networks (ICLR 2025 · similarity 0.83)
- Rethink the Role of Deep Learning towards Large-scale Quantum Systems (ICML 2025 · similarity 0.83)
- Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms (NeurIPS 2024 · similarity 0.82)
- ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks (CVPR 2025 · similarity 0.82)
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.
