Hands-on Machine Learning
Practical implementation of machine learning algorithms, model evaluation, and real-world projects by Hobot Academy.
The Hands-on Machine Learning course at Hobot Academy is designed to bridge the gap between mathematical theory and professional implementation. What sets this curriculum apart is the “Dual-Implementation” philosophy: every algorithm is first derived and implemented from scratch using NumPy to master the underlying logic, followed by an industry-standard implementation using Scikit-Learn.
The complete curriculum, including technical deep-dives, Jupyter Notebooks, and datasets, is maintained directly on the official repository.
🚀 VIEW PROJECTS & CODE ON GITHUB
Course Syllabus
The repository follows a structured, session-based roadmap (S01–S27), transitioning from foundational statistics to advanced unsupervised learning:
- Phase 1: Foundations & Visualization
-
S01-S03: Review of Python for AI and Numerical Computing with NumPy. -
S04-S05: Statistical Foundations (Normal Distribution) and Data Visualization with Matplotlib & Seaborn.
-
- Phase 2: Supervised Learning (Regression)
-
S06-S11: Theoretical and Coding sessions for Linear, Polynomial, and Logistic Regression. -
S12-S13: Advanced Data Preprocessing, Cleaning, and Regularization techniques.
-
- Phase 3: Supervised Learning (Classification)
-
S14-S17: Instance-based learning with KNN and Probabilistic models via Naive Bayes. -
S18-S21: Advanced Classification using Support Vector Machines (SVM) and Decision Trees.
-
- Phase 4: Unsupervised Learning & Dimensionality Reduction
-
S22-S25: Clustering analysis using K-Means and DBSCAN. -
S26-S27: Feature extraction and Dimensionality Reduction through Principal Component Analysis (PCA).
-
👩🏫 Instructor: Zahra Amini
Zahra Amini is an AI Programmer and the founder of Hobot Academy. She specializes in creating structured educational content for data science and machine learning.
