Summary of Efficient Training Of Probabilistic Neural Networks For Survival Analysis, by Christian Marius Lillelund et al.
Efficient Training of Probabilistic Neural Networks for Survival Analysis
by Christian Marius Lillelund, Martin Magris, Christian Fischer Pedersen
First submitted to arxiv on: 9 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers investigate novel methods for training probabilistic neural networks that can accurately predict patient survival times while efficiently handling large datasets. The study compares Variational Inference (VI) with alternative techniques like Monte Carlo Dropout (MCD) and Spectral-normalized Neural Gaussian Process (SNGP). Results show that MCD achieves comparable performance to VI in terms of concordance index and mean absolute error, but provides better calibrated uncertainty estimates. SNGP also outperforms VI in providing D-calibrated survival functions. The findings suggest that non-VI techniques can be viable alternatives for survival analysis in high-dimensional datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores new ways to train deep learning models that predict patient survival times accurately and efficiently handle large amounts of data. Researchers compared different methods, including Variational Inference (VI), Monte Carlo Dropout (MCD), and Spectral-normalized Neural Gaussian Process (SNGP). They found that MCD performed similarly to VI in predicting survival times, but provided better uncertainty estimates. SNGP also outperformed VI in providing accurate survival predictions. This study shows that there are alternative methods to VI for predicting patient survival times. |
Keywords
* Artificial intelligence * Deep learning * Dropout * Inference
