Welcome to the machine learning practices repository! This repository contains four directories, each focusing on a specific machine learning practice.
- Practice 1: Decision Trees and KNN
- Practice 2: Stroke Prediction and Insurance Cost Prediction
- Practice 3: Simple Neural Network Implementation and Training
- Practice 4: Implementing DBSCAN Algorithm and Clustering
- Practice Number 1
- Goals: Implement and evaluate Decision Trees and K-Nearest Neighbors (KNN) algorithms. Explore hyperparameter tuning techniques and model evaluation.
- Practice Number 2
- Goals: Predict stroke occurrence and insurance costs using Support Vector Classifier (SVC) and Linear Regression models. Handle missing values, feature scaling, and evaluate model performance.
-
Goals: Implement a simple neural network from scratch and train it using the backpropagation algorithm. Gain insights into the training process and parameter optimization.
-
- Practice Number 4
- Goals: Implement the DBSCAN algorithm for density-based clustering. Visualize clustering results and explore different hyperparameter combinations.
Feel free to explore each practice directory for detailed implementations, code, and results!😃