Machine Learning Engineer
Implement ML from first principles. Python deep, then build a neural network and a GPT-style transformer from scratch. Plus the linear algebra that makes everything work (Octave / Fortran).
Course sequence
- 01
Python Fundamentals
Not startedStart from zero and build a solid Python foundation. You will learn variables, data types, conditionals, loops, and string manipulation through hands-on exercises with real code execution.
beginnerpython13 lessons~3h - 02
Python in Practice
Not startedGo beyond the basics. Master lists, dictionaries, functions, and file handling through practical exercises that mirror real-world programming tasks.
intermediatepython12 lessons~3h - 03
Advanced Python
Not startedLevel up with object-oriented programming, generators, decorators, and real-world patterns. This course is for programmers who know the fundamentals and want to write professional Python.
advancedpython9 lessons~2h - 04
SQL Fundamentals
Not startedLearn SQL: the language for talking to databases. Used by literally every backend that stores anything. SELECT, JOIN, GROUP BY, aggregates, subqueries — once you have these you can answer any question your data can answer.
beginnersql10 lessons~3h - 05
SQL Intermediate
Not startedLevel up from SQL Fundamentals. Subqueries, CTEs, window functions, set operations, transactions, indexes. The SQL features serious analytics and reporting use every day.
intermediatesql7 lessons~2h - 06
Octave Fundamentals
Not startedLearn GNU Octave: a free, MATLAB-compatible language for numerical computing. Linear algebra, signal processing, statistics — all built into the syntax. If you know MATLAB, you already know 95% of Octave.
beginneroctave7 lessons~2h - 07
Octave Intermediate
Not startedLevel up from Octave Fundamentals. Cell arrays, structs, anonymous functions, file I/O, linear algebra. The features that turn Octave from teaching tool to research-grade computing.
intermediateoctave7 lessons~2h - 08
Build a Neural Network
Not startedBuild an MNIST classifier from scratch in NumPy: neurons, dense layers, sigmoid/ReLU/softmax, MSE/cross-entropy loss, manual backpropagation, gradient descent + Adam, training loop, and the path to PyTorch/TensorFlow.
advanced25 lessons~6h - 09
Build a Transformer (GPT-style)
Not startedBuild a tiny GPT in NumPy: token + position embeddings, layer normalization, scaled dot-product self-attention, multi-head attention with causal mask, feed-forward networks, residual connections, sampling (greedy, top-k, top-p), and the architecture behind ChatGPT, Claude, Llama.
advanced14 lessons~4h
Create a free account to track your progress across this path.