This report provides an analysis of machine learning models applied to the Wisconsin and MNIST datasets. The study employs logistic regression for both binary and multiclass classification tasks. The Wisconsin dataset is utilized for binary classification, while the MNIST dataset is used for multiclass classification. The report explores the application of L1 and L2 regularization techniques to improve model accuracy. The analysis includes the calculation of accuracy, precision, recall, and F1-score, along with the generation of confusion matrices. The report also addresses the concepts of overfitting and underfitting, providing graphical representations and strategies for mitigation. The results demonstrate the effectiveness of the models, with the Wisconsin dataset achieving over 90% accuracy and the MNIST dataset achieving over 80% accuracy. The conclusion emphasizes the importance of data preprocessing, handling missing values, and the significance of regularization in building robust machine learning models.
![[object Object]](/_next/static/media/star-bottom.7253800d.svg)
