Machine Learning

A comprehensive self-paced course covering essential machine learning concepts, algorithms, and practical applications

Start Learning

📚 24 Modules

Comprehensive curriculum from basics to advanced topics

🎯 Self-Paced

Learn at your own speed with flexible scheduling

💻 Hands-On

Practical exercises and real-world projects

🔬 Research-Based

Latest methodologies and industry best practices

Fundamentals

1

Python Gentle Intro

Lecture
  • First for-loop in Python, compilation and interpretation
  • Objects representation: id, type and value
  • Size of int
  • PyCharm IDE and JetBrains Academy plugin
▶️ Video 📑 Slides
1

Types, mutables and immutables

Practice
  • Main uses of the language
  • Dive into mutables and immutables
  • Standart types algorithmic complexity
📑 Slides
1

Introduction to Python

Easy
  • Variables, Strings, Data structures
  • Condition expressions, Loops, Functions
  • Modules and packages
  • Classes and objects, File input and output
▶️ Video 📝 JB plugin-course

Q1

Python Quiz for self-check

Quiz
  • Test your knowledge of Python fundamentals
  • 8 questions covering Python basics
  • Immediate feedback and explanations
📝 Take Quiz

2

Indexing, slices, comprehensions and collections

Practice
  • Indexing, slices, unpacking
  • List and dict comprehensions
  • Module collections and their algorithmic complexities
  • Garbage collector and reference count
📑 Slides
2

Numpy and Pandas

Lecture
  • Numpy: intro and ndarray
  • Slices and Indexing
  • Concatenation and broadcasting
  • Pandas DataFrames, Titanic Dataset
▶️ Video 📑 Slides
2

Numpy

Easy
  • Array Basics, Array Indexing and Slicing
  • Transposing, Sorting and Concatenating
  • Compare Search, Array Math
  • Arrays of String and Unicode Values
📝 JB plugin-course
3

Intro to Machine Learning

Lecture
  • Types of ML: Supervised, Unsupervised, Reinforcement
  • Linear Regression in sklearn
  • Overfitting, train/test split
  • Significant events in machine learning history
▶️ Video 📑 Slides
3

Matrix differentiation

Practice
  • Recap of function differentiation
  • Differential
  • Matrix differential properties
  • Hessian
📑 Slides
3

Pandas

Medium
  • Understanding Pandas data structures: DataFrame and Series
  • Data summarizing, filtering, sorting
  • Implementation of your own TED Talks simple recommendation model
📝 JB plugin-course

Q2

Numpy, Pandas and ML

Quiz
  • Test your knowledge of Numpy, Pandas and ML fundamentals
  • 15 questions covering ML basics
📝 Take Quiz

4

Linear models, Stochastic Gradient Descent

Lecture
  • Loss functions examples
  • Linear classifier, Regularization
  • The Stochastic Gradient (SG, SAG) method
  • Likelihood maximization and minimization of the empirical risk
▶️ Video 📑 Slides
4

Linear models

Practice
  • Analytical and numerical approaches to solve linear regression
  • from sklearn.linear_model import LinearRegression
  • How to choose learning rate
📑 ipynb
4

Gradient Descent

Easy
  • Full and Stochastic GD
  • Momentum and Adagrad
  • Regularization and Linear Regression
📝 JB plugin-course
5

Logical Rules and Decision Trees

Lecture
  • Logical Rules
  • Decision Trees
  • ID3 algorithm
  • Measurement of uncertainty
▶️ Video 📑 Slides
5

Metric methods

Practice
  • K-nearest neighbors classifier (KNN)
  • Parzen Window Method
  • Potential Function Method
  • Nadaraya-Watson Estimator
📑 ipynb
5

Logical Rules and Decision Trees

Easy
  • Losses in Decision Trees
  • Gini Index
  • Entropy
📝 Cogniterra

Q3

Linear and Logical

Quiz
  • Test your knowledge of Linear and Logical models
  • 16 questions
📝 Take Quiz

6

Ensembles, random forest and gradient boosting

Lecture
  • Simple and weighted voting, mixture of experts
  • Boosting, bagging, RSM
  • XGBoost, CatBoost, LightGBM
  • Random forest
▶️ Video 📑 Slides
6

Ensembles

Practice
  • Bagging, Boosting
  • GradBoost, XGoost, CatBoost, LightGBM
  • Random forest
📑 ipynb
6

Binary Classification Competition

Medium
  • Tabular data
  • Gradient Boosting
📝 Kaggle
7

Intro to neural networks and backpropagation

Lecture
  • Rise of neural networks
  • Expressive power of neural network
  • Backpropagation algorithm
▶️ Video 📑 Slides
7

Backpropagation

Practice
  • MNIST dataset
  • Computational graph
  • Micrograd by Andrej Karpathy
📑 ipynb
7

Simple Neural Network in Numpy

Medium
  • Forward pass
  • Backpropagation
📝 JB plugin-course

Q4

Ensembles and Neural Net

Quiz
  • Test your understanding
  • 14 questions
📝 Take Quiz

8

Recurrent neural networks basics

Lecture
  • Disadvantages of Feed-Forward Neural Networks
  • Architectures of Recurrent Networks
  • Vanilla RNN, LSTM, GRU
▶️ Video 📑 Slides
8

Building char-rnn from scratch

Practice
  • Data and random initialization
  • Cross-entropy loss
  • Train and sample
📑 ipynb
8

ML Contest

Hard
  • Linear models
  • Decision trees
  • Simple neural net
📝 Cogniterra
9

PyTorch Tutorial

Practice
  • Working with tensors
  • Autograd and Neural Network example
  • Demo model for word classification
▶️ Video 📑 ipynb
9

PyTorch Introduction

Easy
  • Tensors and Autograd
  • Word Window Classifier
📝 JB plugin-course
9

Language modeling: bigrams and multi layers perceptron

Lecture
  • Makemore on the bigrams level
  • Adding prior for more robust predictions
  • Multi Layer Perceptron
▶️ Video 📑 ipynb

Q5

RNNs and MLP

Quiz
  • Test your understanding
  • 16 questions
📝 Take Quiz

10

Convolutional Neural Networks

Lecture
  • Brief history of computer vision
  • The progress of convolutional neural nets
  • Details of AlexNet model
▶️ Video 📑 Slides
10

CNN

Practice
  • trainer(), train_epoch() and train_on_batch
  • LeNet architecture
  • Layers visualization, tensorboard and lime
📑 ipynb
10

Image Classification Competiton

Hard
  • The Street View House Numbers dataset
  • Progressive checkpoints with CNNs' architectures
📝 Kaggle
11

Attention mechanism, Transformer architecture

Lecture
  • Disadvantages of RNNs
  • Attention for machine translation and annotating images
  • Architecture of a Transformer model
  • BERT and masked language modeling
▶️ Video 📑 Slides
11

Attention

Practice
  • Gathering parallel texts
  • Attention in RNN
  • Transformer model
📑 ipynb
11

Backpropagation and MLP

Hard
  • Different layers implementation
  • Auto Backpropagation
📝 JB plugin-course
12

Building GPT-2 from scratch

Lecture
  • "Attention is all you need"
  • Math trick in self-attention
  • Layer normalization and dropout
▶️ Video 📑 ipynb
12

Tokenization

Practice
  • We must tokenize information for computer
  • Byte-pair encoding algorithm
  • Sentencepiece BPEs (Llama and Mistral series)
📑 ipynb
12

Transformers

Medium
  • Tokenization and Embeddings
  • Attention Heads
  • Transformer Block
📝 JB plugin-course

Q6

Attention and Transformers

Quiz
  • Test your understanding
  • 16 questions
📝 Take Quiz

13

Bayesian methods Intro

Lecture
  • Conditional probability and Bayes' theorem
  • Comparison of Frequentist and Bayesian approaches
  • Markov Chain Monte Carlo (MCMC) and Gibbs sampling
📑 Slides
13

Bayesian methods

Practice
  • Conjugate distributions
  • Maximum Likelihood Estimation
  • Metropolis-Hastings algorithm
📑 ipynb

Advanced

14

Detection and Segmentation in Computer Vision

Lecture
  • Detection and Segmentation tasks
  • IoU, Average Precision
  • Fast R-CNN, UNet
▶️ Video 📑 Slides
15

Semi- and unsupervised learning, clustering

Lecture
  • K-Means Clustering
  • Principal Component Analysis (PCA)
  • t-SNE, MAP, Other Dimensionality Reduction Methods
  • DBSCAN Clustering, Hierarchical Clustering
▶️ Video 📑 Slides
15

Clustering

Practice
  • K-Means
  • DBSCAN
  • Hierarchical Clustering
  • Self-training and co-learning
📑 ipynb
16

Expectation-Minimization algorithm

Lecture
  • Kullback-Leibler Divergence
  • Motivating example with multiple Gaussians
  • Probabilistic Interpretation of the Principal Component Analysis
📑 Slides
16

Expectation-Minimization algorithm

Practice
  • Problem formulation
  • Revise lower-bound definition
  • EM implementation, results
📑 ipynb
16

Clustering and EM algorithm

Hard
  • EM algorithm
  • Aggregation
  • Topic Modeling, Clusterization
📝 JB plugin-course

Q7

Computer Vision and Clustering

Quiz
  • Test your understanding
  • 16 questions
📝 Take Quiz

17

CLIP. Fine-tuning and lin-prob

Lecture
  • Pre-training and fine-tuning
  • CLIP: Contrastive Language-Image Pre-training
  • Zero-shot CLIP is a robust model
▶️ Video 📑 Slides
18

Generative vs Discriminative models, VAE, GANs

Lecture
  • Difference between Generative and Discriminative models
  • What is GAN and how to train it?
  • Variational Autoencoder architecture, reparameterization trick
▶️ Video 📑 Slides
18

Generative models

Practice
  • Tensorboard
  • Autoencoder: linear, CNN, VAE
  • GAN for MNIST
📑 ipynb

Q8

CLIP, fine-tuning and GANs

Quiz
  • Test your understanding
  • 17 questions
📝 Take Quiz

19

Reinforcement Learning Intro

Lecture
  • Reward modeling and Optimal Control Assumptions
  • Environments and Observations
  • Markov Decision Process
▶️ Video 📑 Slides
19

RL Intro

Practice
  • RiverSwim Problem
  • Q-learning implementation
  • Deep Q-Network
📑 ipynb

20

From AlphaGo to AlphaZero

Lecture
  • TD Gammon
  • Why is Go really hard for computer?
  • Inside AlphaGo: SL and RL policies, MCTS
  • Inside AlphaZero
▶️ Video 📑 Slides
20

AlphaZero from Scratch

Hard
  • Monte-Carlo Tree Search
  • Deep reinforcement learning
  • AlphaZero for TicTacToe and Connect4
📝 JB plugin-course

Q9

RL and AlphaZero

Quiz
  • Test your understanding
  • 17 questions
📝 Take Quiz

21

Stable Diffusion

Lecture
  • Noising and denoising
  • Pipeline of Stable Diffusion
  • Adding Text Encoder and CLIP
▶️ Video 📑 Slides
21

Efficient Neural Network Training

Practice
  • Floating Points 101
  • Fully sharded data parallel (FSDP)
  • Parameter Efficient Fine-Tuning (PEFT)
  • Low-Rank Adaptation (LoRA)
📝 Slides
21

EM and Neural Network Theory

Hard
  • Mixture distributions
  • word2vec
  • Optimal rewards
📝 ipynb
22

NLP Crash Intro

Lecture
  • Word2vec and GloVe
  • Transformers, BERT and NLP tasks
  • Fine-tuning and PEFT
▶️ Video 📑 ipynb 📑 Slides
22

NLP Intro

Practice
  • Lemmatization and n-grams
  • Word2Vec model
  • Vector's similarity
📝 ipynb
22

Build your own Jarvis

Hard
  • LLMs integration
  • Voice Recognition and Generation
  • Bonus tasks
📝 md

Q10

Diffusion and NLP

Quiz
  • Test your understanding
  • 15 questions
📝 Take Quiz

23

Model compression and Mixture-of-Experts

Lecture
  • Quantization: reduce the number of bits
  • Pruning and Distillation
  • Mixture of Experts: Sparse Computation
📑 Slides
24

Agents with LangChain

Lecture
  • How LLMs use tools?
  • Chatbot's memory
  • Vector Stores for Embeddings
▶️ Video 📝 ipynb
24

Build Simple AI Agent

Hard
  • Tools for LLM
  • Agentic frameworks
  • Create your own AI agent
📝 Cogniterra
25

Write ML Blogpost

Medium
  • Find the best paper for you
  • Write and public the post about the paper
📝 md

Prerequisites

🐍 Python

Basic programming experience

🔢 Mathematics

Linear algebra and calculus basics