Summary of Dnn-gditd: Out-of-distribution Detection Via Deep Neural Network Based Gaussian Descriptor For Imbalanced Tabular Data, by Priyanka Chudasama et al.
DNN-GDITD: Out-of-distribution detection via Deep Neural Network based Gaussian Descriptor for Imbalanced Tabular Data
by Priyanka Chudasama, Anil Surisetty, Aakarsh Malhotra, Alok Singh
First submitted to arxiv on: 2 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 A novel deep learning-based algorithm for detecting out-of-distribution samples in imbalanced tabular datasets is introduced. The Deep Neural Network-based Gaussian Descriptor for Imbalanced Tabular Data (DNN-GDITD) can be used on top of any deep neural network to improve classification accuracy and detect unknown data points using spherical decision boundaries. The algorithm assigns confidence scores to test data, categorizing them as known classes or out-of-distribution samples. Compared to three existing OOD detection algorithms, DNN-GDITD demonstrates effectiveness in both imbalanced and balanced scenarios on various tabular datasets, including synthetic and publicly available datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to spot unusual data is developed for tables of numbers. This method, called Deep Neural Network-based Gaussian Descriptor for Imbalanced Tabular Data (DNN-GDITD), can be used with any deep learning model to make better predictions on imbalanced data and find unknown patterns. The algorithm gives scores to new data, saying whether it’s known or not. Tests show that this method works well compared to other ways of finding unusual data. |
Keywords
» Artificial intelligence » Classification » Deep learning » Neural network
