ML Intensive for TLF (5 lessons, 2.5h each)

A one-week intro to Machine Learning: from Python and NumPy to gradient descent, trees, backpropagation and recurrent neural networks. You will learn how models make predictions, measure their mistakes and improve themselves step by step. By the end of the course, concepts such as loss functions, stochastic gradient descent, backpropagation and RNNs will no longer sound like mysterious spells.

Everything here is open. Sign in and enter your teacher’s group code if you want your homework counted.

• Lecture 1. Python Refresher2026-08-17delivered

  In class: py_basics/middle_value_of_triple, py_basics/fizz_buzz, py_functional/flat_it

  Homework: 26 tasks · due Aug 18

• Lecture 2. NumPy and Pandas2026-08-18delivered

  In class: numpy_basics/reverse_vector, numpy_basics/make_immutable, numpy_basics/matrix_product, numpy_basics/to_column, numpy_basics/pairwise_distances, numpy_combine/stack_columns, numpy_indexing/mask_negate

  Homework: 18 tasks · due Aug 19

• Lecture 3. Introduction to Machine Learning2026-08-19delivered

  In class: numpy_linalg/normalize_rows, numpy_manipulation/replace_nans, numpy_manipulation/pad_border, numpy_reductions/moving_average

  Homework: 15 tasks · due Aug 20

• Lecture 4. Linear models, Stochastic Gradient Descent2026-08-20delivered

  In class: py_basics/iterate_me, numpy_manipulation/swap_rows, pandas_manipulation/clean_data

  Homework: 7 tasks · due Aug 21

• Lecture 5. Neural networks and backpropagation2026-08-21

  In class: ml_interview/image_rotation

  Homework: 3 tasks · due Aug 22