Rebel Alchemy · Browse communities · Search · Pricing · About us · Support

Applied Machine Learning

Machine Learning

Level: Beginner

Duration: 60 minutes

$120

About

This course introduces students to the practical side of Machine Learning using Python. Emphasizing intuition over theory, students will learn how to build, train, and evaluate machine learning models using real-world datasets. The course focuses on linear regression, classification, dimensionality reduction, and neural networks, using industry-standard libraries such as Scikit-learn, Pandas, Matplotlib. By the end of the course, students will be able to apply supervised and unsupervised learning techniques to real problems in data science and engineering. Ideal for future engineers, data analysts, and researchers ready to dive into the AI revolution. This class includes the basics of plotting and visualizing data, importing datasets, searching for datasets, pre-processing techniques, Pandas and using Colab notebooks. Total hours for this class is 20 hours.

Learning Goals

Section 1: Data Exploration Tools (Pandas, Matplotlib, Colab, Kaggle) By the end of this section, students will be able to: Load and explore datasets using Pandas (read_csv, .head(), .describe(), etc.). Create data visualizations with Matplotlib and Seaborn (bar plots, scatter plots, histograms). Use Google Colab to write, run, and share Python notebooks. Find, download, and submit ML datasets and notebooks on Kaggle.

Section 2: Data Preprocessing By the end of this section, students will be able to: Distinguish between numerical and categorical features. Handle missing data through imputation and deletion. Normalize and standardize datasets for better model performance. Encode categorical features using one-hot and label encoding. Split datasets into training and testing sets using train_test_split.

Section 3: Linear Regression By the end of this section, students will be able to: Understand the principles behind simple and multiple linear regression. Fit regression models using scikit-learn's LinearRegression. Evaluate regression performance using MSE, RMSE, and R² Score. Visualize regression results with scatter plots and regression lines. Apply linear regression to real-world datasets (e.g., predicting housing prices).

Section 4: Classification Models By the end of this section, students will be able to: Train and evaluate logistic regression, k-nearest neighbors, and decision trees. Understand model overfitting and underfitting. Use confusion matrix, accuracy, precision, recall, and F1-score to assess performance. Plot and interpret ROC curves and AUC values. Apply classification to datasets like spam detection or disease diagnosis.

Section 5: Dimensionality Reduction with PCA By the end of this section, students will be able to: Understand the intuition behind Principal Component Analysis (PCA). Use PCA to reduce high-dimensional data to 2D or 3D for visualization. Apply PCA to improve model training time and reduce noise. Visualize principal components and interpret explained variance. Combine PCA with classification tasks to compare model performance with/without PCA.

Teacher

Open this page on Rebel Alchemy