Research map / Architectures and efficiency / RNNs and normalization
GPEX, A Framework For Interpreting Artificial Neural Networks
Amir Akbarnejad, Gilbert Bigras, Nilanjan Ray
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 |
|---|---|---|---|
| use GPEX instead of representer point selection for label correction | dataset debugging · Cifar10 automobile vs horse | instances shown to reach about 90% accuracy: 7000 -> 4000 | Improved |
| use GPEX instead of influence functions for label correction | dataset debugging · Cifar10 automobile vs horse | instances shown to reach about 90% accuracy: 7000 -> 4000 | Improved |
| use influence functions instead of GPEX for spotting corrupted labels | dataset debugging · Cifar10 automobile vs horse | corrupted labels found per instances shown | Hurt |
| use GPEX instead of representer point selection for spotting corrupted labels | dataset debugging · Cifar10 automobile vs horse | corrupted labels found per instances shown | Improved |
| smaller dataset with few inducing points | GPEX on DogsWolves · DogsWolves | Pearson correlation between GP mean and ANN | Hurt |
| apply GPEX to attention submodules | GPEX · Cifar10, MNIST, Kather | Pearson correlation between GP mean and ANN | Improved |
Closest papers by meaning
- Approximate Inference Turns Deep Networks into Gaussian Processes (NeurIPS 2019 · similarity 0.86)
- Deep Neural Networks as Gaussian Processes (ICLR 2018 · similarity 0.86)
- Spherical Inducing Features for Orthogonally-Decoupled Gaussian Processes (ICML 2023 · similarity 0.85)
- Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference (NeurIPS 2024 · similarity 0.85)
- Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study (NeurIPS 2025 · similarity 0.83)
- Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization (NeurIPS 2024 · similarity 0.83)
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.
