Research map / Architectures and efficiency / RNNs and normalization
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation
Liwei Wang, Lunjia Hu, Jiayuan Gu, Zhiqiang Hu, Yue Wu, Kun He, John Hopcroft
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 |
|---|---|---|---|
| Train identical CNN architectures from different random initializations | VGG and ResNet networks · CIFAR10 and ImageNet validation sets | maximum matching similarity | Mixed |
| Compare local neuron-group matches across independently initialized networks | VGG and ResNet layers · Layers close to input and output | simple-match size distribution | No clear effect |
Closest papers by meaning
- When Representations Align: Universality in Representation Learning Dynamics (ICML 2024 · similarity 0.89)
- Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity (ICLR 2025 · similarity 0.88)
- How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching (AAAI 2025 · similarity 0.88)
- Formation of Representations in Neural Networks (ICLR 2025 · similarity 0.87)
- Representational Similarity via Interpretable Visual Concepts (ICLR 2025 · similarity 0.87)
- Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks (ICML 2025 · similarity 0.87)
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.
