Machine Learning Path
A technical route for learners who want to move from Python and data analysis into model training, evaluation, algorithms, deep learning, and computer vision.
Use this path when it matches the work you want to do
Choose this path if you want to build and evaluate models, compare algorithms, understand deep learning, and explain model limits responsibly.
Read the skip rule
Do not start here if Python, data cleaning, train-test splits, and basic metrics are still confusing.
Read the path outcome
A model-building portfolio with baseline models, algorithm comparisons, deep learning experiments, error analysis, and responsible-use notes.
Follow the route in this order
The order keeps prerequisites clear. If a course is already comfortable, use its detail page to confirm the syllabus before skipping it.
Python Foundations for AI
Build the Python basics needed for notebooks, data work, automation, and AI examples.
Data Analysis and Visualization with Python
Clean, inspect, join, summarize, visualize, and report on datasets using the Python data stack.
Machine Learning Foundations
Understand training, prediction, baselines, metrics, leakage, overfitting, and model limits.
Applied Machine Learning Algorithms
Choose, compare, tune, inspect, and explain practical machine-learning model families.
Deep Learning Basics with TensorFlow and Keras
Build your first responsible deep learning workflows with tensors, Keras, training, and diagnostics.
Advanced Deep Learning with PyTorch
Learn PyTorch through tensors, autograd, custom training loops, model inspection, and model cards.
Computer Vision and Multimodal AI
Understand images as data, use basic vision pipelines, evaluate outputs, and state responsible limits.
What this route includes
- Python Foundations for AI
- Data Analysis and Visualization with Python
- Machine Learning Foundations
- Applied Machine Learning Algorithms
- Deep Learning Basics with TensorFlow and Keras
- Advanced Deep Learning with PyTorch
- Computer Vision and Multimodal AI
Start the first course, then continue through the path
A model-building portfolio with baseline models, algorithm comparisons, deep learning experiments, error analysis, and responsible-use notes.