Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Natural-Parameter Networks: A Class of Probabilistic Neural Networks
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 Gaussian NPN instead of Dropout1 | MNIST classifier · MNIST test | error rate: 1.33% -> 1.25% | Helped |
| use NPN instead of Dropout | MNIST classifier · MNIST, 100 training examples | error rate: 32.58% -> 29.97% | Helped |
| use NPN instead of Dropout | MNIST classifier · MNIST, 500 training examples | error rate: 15.39% -> 13.79% | Helped |
| use NPN instead of Dropout | MNIST classifier · MNIST, 2,000 training examples | error rate: 8.78% -> 7.89% | Helped |
| use NPN instead of Dropout | MNIST classifier · MNIST, 10,000 training examples | error rate: 3.53% -> 3.28% | Helped |
| use NPN instead of PBP | regression model · Boston Housing | RMSE: 3.01 -> 2.57 | Helped |
| use NPN instead of VAE | representation learner · Citeulike-a | link rank: 980.8 -> 690.9 | Helped |
| use Gaussian NPN instead of SDAE | representation learner · Citeulike-t | link rank: 1356.8 -> 1280.4 | Helped |
| use NPN instead of SDAE | representation learner · arXiv | link rank: 2916.1 -> 2684.1 | Helped |
| add variance information to the Poisson NPN representation (ablation) | Poisson NPN · Citeulike-a | link rank: 5389.7 -> 690.9 | Helped |
| add variance information to NPN representations (ablation) | NPN variants · Citeulike-a | link rank: 935.8 -> 851.7; 823.9 -> 750.6 | Helped |
| add variance information to the Poisson NPN representation (ablation) | Poisson NPN · Citeulike-t | link rank: 9117.2 -> 1354.1 | Helped |
Closest papers by meaning
- Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions (ICLR 2022 · similarity 0.88)
- Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers (ICLR 2019 · similarity 0.87)
- Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models (CVPR 2024 · similarity 0.87)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.86)
- Random-Set Neural Networks (ICLR 2025 · similarity 0.85)
- Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo (ICLR 2025 · 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.