Back to Projects
Machine Learning

White Noise vs L2 Regularization

Investigation of the equivalence between white noise application and L2 regularizer using different datasets.

Course: Machine LearningCo-authors: Fernanda Avendaño, Diego Quezada
White Noise vs L2 Regularization

Objectives

  • 1Verify the equivalence of white noise application and the use of L2 regularizer.

Conclusions

  • The performance of models when applying white noise or L2 regularizer is practically the same on average.
  • In the three datasets there are lambda values such that the effectiveness of the models, measured through MSE, is the same.

Technologies

  • NumPy
  • Pandas
  • Scikit-learn
  • Matplotlib
  • Seaborn
  • FastAPI