Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Understanding Priors in Bayesian Neural Networks at the Unit Level
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 |
|---|---|---|---|
| Increase hidden-layer depth | Fully connected BNN with independent Gaussian weight priors and an activation satisfying the extended envelope property · Hidden-layer unit marginal priors | optimal tail parameter θ: 1/2 -> 1 -> 3/2 -> 5 -> 50 | Mixed |
| Use a bounded activation such as sigmoid or tanh | Bayesian neural network units · Hidden-layer unit marginal priors | tail class | Mixed |
| Apply batch normalization or layer normalization | Feed-forward neural networks · Unit prior tail behavior | optimal tail parameter | No clear effect |
| Apply max pooling or averaging | Convolutional Bayesian neural networks · Pooled unit distributions | optimal tail parameter | No clear effect |
Closest papers by meaning
- Exact marginal prior distributions of finite Bayesian neural networks (NeurIPS 2021 · similarity 0.90)
- Bayesian Neural Network Priors Revisited (ICLR 2022 · similarity 0.90)
- Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights (NeurIPS 2020 · similarity 0.89)
- A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors (ICLR 2024 · similarity 0.87)
- Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes (ICLR 2024 · similarity 0.86)
- Critical feature learning in deep neural networks (ICML 2024 · similarity 0.86)
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.