Research map / Architectures and efficiency / RNNs and normalization
Memorization Capacity of Neural Networks with Conditional Computation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use conditional computation (synthesized conditional network) instead of unconditional network for memorization | ReLU memorization network · Memorization of n patterns | operations per input: O(sqrt(n)) to O(log n) | Helped |
| Theoretical lower bound: any conditional network needs Omega(log n) operations per input under rank condition | Conditional ReLU networks · Memorization of n patterns | operations per input | No clear effect |
Closest papers by meaning
- The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets (NeurIPS 2025 · similarity 0.86)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.86)
- Factual recall in linear associative memories: sharp asymptotics and mechanistic insights (NeurIPS 2026 · similarity 0.85)
- On the Optimal Memorization Capacity of Transformers (ICLR 2025 · similarity 0.85)
- Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise (NeurIPS 2026 · similarity 0.85)
- The Effect of Weight Precision on the Neuron Count in Deep ReLU Networks (ICML 2024 · similarity 0.85)
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.