Summary of An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction Using Vae-based Data Augmentation, by Farah Alsafadi et al.
An Investigation on Machine Learning Predictive Accuracy Improvement and Uncertainty Reduction using VAE-based Data Augmentation
by Farah Alsafadi, Mahmoud Yaseen, Xu Wu
First submitted to arxiv on: 24 Oct 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 This research paper explores the potential of deep generative learning to address data scarcity in nuclear engineering. By leveraging ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and available large datasets, the study aims to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. The researchers investigate whether VAE-based data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, they quantify DNN prediction uncertainties using Bayesian Neural Networks (BNN) and conformal prediction (CP). To test the proposed methodology, the study uses TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. The results show that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved prediction confidence intervals, and reduced prediction uncertainties. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study looks at how to fix a problem in nuclear engineering where there isn’t enough data to train machines learning models accurately. They use special computer programs called generative models to create new fake data that looks like real data. This helps the machine learning model make better predictions about what will happen in different situations. The researchers tested this method using data from a nuclear reactor test and found that it worked well, making their predictions more accurate and confident. |
Keywords
» Artificial intelligence » Data augmentation » Machine learning » Neural network » Variational autoencoder
