A curated collection of my notebooks created for university courses in Machine Learning, Data Science and Information Retrieval.

---

• Place Recognition
  Using SIFT together with custom implementation of KNN, ANN (ANN, RKDT) to identify famous locations.
  Open in Colab

• Song Analysis
  Includes EDA, data preprocessing, pipelining, feature engineering, and unsupervised clustering
  Open in Colab

• Song Analysis Presentation
  Highlights key findings and insights
  View Presentation

• Forest Cover
  End-to-end ML workflow with EDA, preprocessing, feature engineering, classification (SVM, KNN, RF), clustering (KMeans, Hierarchical, GMM), and dimensionality reduction (PCA, t-SNE).
  Open in Colab

• MNIST Dimensionality Reduction & Classification
  PCA and feature selection on MNIST, model comparison (RF, KNN) across original/reduced datasets, performance vs. runtime trade-offs, and t-SNE visualization.
  Open in Colab

• **Synthetic data classification and Outlier Detection **
  Random Forest and PCA-based feature importance, KNN classification using PC1, statistical and ML-based outlier detection methods, and PCA visualization of anomalies.
  Open in Colab

nifty little reverse-index i implemented for Information Retreival course: https://colab.research.google.com/drive/1a3CdKKj0aM0p1XGfiI-eLEjM-7qk0I0D?usp=sharing

---