Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Scalar-on-Image Regression with a Spatially Varying Single-layer Neural Network Prior
Ben Wu, Keru Wu, Jian Kang
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 |
|---|---|---|---|
| increase hidden units from 1 (STGP) to 5 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 47.9 -> 15.4 | Improved |
| increase hidden units from 3 to 5 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 29.2 -> 15.4 | Improved |
| increase hidden units from 5 to 7 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 15.4 -> 16.5 | Hurt |
| increase hidden units from 5 to 10 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 15.4 -> 17.2 | Hurt |
| use soft threshold 5 instead of 0 (no selection) (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 38.5 -> 15.5 | Improved |
| raise threshold from 5 to 6 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 15.5 -> 22.1 | Hurt |
| raise threshold from 5 to 7 (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 15.5 -> 28.4 | Hurt |
| use MSE kernel instead of squared exponential kernel (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 17.9 -> 15.4 | Improved |
| use MSE kernel instead of Matern kernel (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 18.6 -> 15.4 | Improved |
| use MSE kernel instead of exponential kernel (ablation) | SV-NN · Synthetic nonlinear classification (train size 200) | error rate (%): 19.2 -> 15.4 | Improved |
| use SV-NN instead of CNN with matching structure | CNN · Synthetic nonlinear classification (train size 200) | error rate (%): 20.4 -> 15.5 | Improved |
| use SV-NN instead of BNN with limited samples | BNN · MNIST 4 vs 7 (n=10 per digit) | error rate (%): 18.3 -> 4.6 | Improved |
Closest papers by meaning
- Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior (ICLR 2025 · similarity 0.89)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.85)
- Deep Kernel Posterior Learning under Infinite Variance Prior Weights (ICLR 2025 · similarity 0.85)
- Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo (ICLR 2025 · similarity 0.85)
- Sparse Bayesian Deep Learning for Cross Domain Medical Image Reconstruction (AAAI 2024 · similarity 0.84)
- A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors (ICLR 2024 · similarity 0.84)
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.
