FastAI is an incredibly convenient and powerful machine learning library bringing Deep Learning (DL) to the masses. I was motivated to write this article while troubleshooting some issues related to training a model for a binary classification task. My objective is to walk you through the steps required to a build a simple and effective DL model using FastAI for a tabularimbalanced dataset while avoiding the mistakes that I had made. The discussion in this article is organized according to the sections listed below.

  1. Dataset
  2. Sample Code
  3. Code Breakdown
  4. Comparison Of FastAI to PySpark ML & Scikit-Learn
  5. Conclusion

#fastai #cross-entropy #imbalanced-data #tabular-data #deep-learning

Deep Learning With Weighted Cross Entropy Loss On Imbalanced Tabular Data Using FastAI
4.40 GEEK