Artem Ryblov’s Data Science Weekly

Mastering PyTorch by Ashish Ranjan Jha

Dive into the world of deep learning with "Mastering PyTorch." With this book, you'll uncover how to use PyTorch effectively to build and deploy advanced neural network models, from convolutional networks for vision tasks to transformers for language processing. You'll also explore cutting-edge topics, such as generative and multimodal models, and learn optimization strategies for faster training and deployment.

What this Book will help you:
• Build convolutional and recurrent neural networks for practical tasks.
• Deploy PyTorch models on mobile platforms and cloud infrastructures.
• Optimize training using multi-GPU setups and mixed-precision techniques.
• Leverage PyTorch libraries like Hugging Face and PyTorch Lightning for enhanced workflows.
• Implement explainable AI solutions using PyTorch's Captum library.

Link: Book

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #dl #pytorch #deeplearning

@data_science_weekly

Complete Docker Course - From BEGINNER to PRO

Learn Docker and containers to improve your software systems! 🐳 📦

This course covers everything from getting started all the way through building a containerized web application and deploying it to the cloud!

Timestamps:
00:00 - Introduction
04:40 - History and motivation
30:27 - Technology overview
40:30 - Installation and set up
47:15 - Using 3rd party container images
48:06 - Understanding container data and docker volumes
1:13:00 - Demo application
1:28:37 - Building container images
2:23:46 - Container registries
2:33:45 - Running containers
3:02:36 - Container security
3:06:58 - Interacting with Docker objects
3:18:36 - Development workflow
3:52:05 - Ephemeral environments with Shipyard
4:07:17 - Deploying containers
4:42:59 - Final wrap up

Link: YouTube

Navigational hashtags: #armknowledgesharing #armcourses
General hashtags: #mlops #docker #containers

@data_science_weekly

Code Complete by Steve McConnell

Widely considered one of the best practical guides to programming, Steve McConnell’s original CODE COMPLETE has been helping developers write better software for more than a decade.

Now this classic book has been fully updated and revised with leading-edge practices―and hundreds of new code samples―illustrating the art and science of software construction. Capturing the body of knowledge available from research, academia, and everyday commercial practice, McConnell synthesizes the most effective techniques and must-know principles into clear, pragmatic guidance.

No matter what your experience level, development environment, or project size, this book will inform and stimulate your thinking―and help you build the highest quality code.

Discover the timeless techniques and strategies that help you:
• Design for minimum complexity and maximum creativity
• Reap the benefits of collaborative development
• Apply defensive programming techniques to reduce and flush out errors
• Exploit opportunities to refactor―or evolve―code, and do it safely
• Use construction practices that are right-weight for your project
• Debug problems quickly and effectively
• Resolve critical construction issues early and correctly
• Build quality into the beginning, middle, and end of your project

Link: Book

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #programming #cleancode

@data_science_weekly

ML/Research Engineer interviews 2025

Recently author went through a lot of interviews with some fancy AI companies (Anthropic, Deepmind, Midjourney, Recraft, Black Forest Labs, Runway, Suno), also FAANG, also a lot of smaller startups. He didn’t necessarily progress far into the stages for all of them but got some offers in the end, e.g. from Perplexity.

This article is an attempt to summarize his observations and learnings - the questions being asked, his mistakes on different stages, how to prepare and useful tips and resources. Basically the things he wish he knew before starting the process and which will be useful anyway in the future.

Link: Site
Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #ml #dl #ai #interview #interviewprep #interviewpreparation

@data_science_weekly

10-202: Introduction to Modern AI by Zico Kolter

This course provides an introduction to how modern AI systems work. By “modern AI”, we specifically mean the machine learning methods and large language models (LLMs) behind systems like ChatGPT, Gemini, and Claude. [Note] Despite their seemingly amazing generality, the basic techniques that underlie these AI models are surprisingly simple: a minimal LLM implementation leverages a fairly small set of machine learning methods and architectures, and can be written in a few hundred lines of code.

This course will guide you through the basic methods that will let you implement a basic AI chatbot. You will learn the basics of supervised machine learning, large language models, and post-training. By the end of the course you will be able to write the code that runs an open source LLM from scratch, as well as train these models based upon a corpus of data. The material we cover will include:
• A brief history of AI
• Supervised machine learning
• Linear models
• Loss functions and optimization
• Neural networks
• Large language models
• Self attention and transformers
• Tokenizers
• Efficient inference
• Post-training
• Supervised fine tuning
• Alignment and instruction tuning
• Reasoning models and reinforcement learning
• Safety and security of AI systems

The topics above are a general framing of what the course will cover. However, as this course is being offered for the first time in Spring 2026, some elements are likely to change over the first offering.

Links:
• Course
• YouTube

Navigational hashtags: #armknowledgesharing #armcourses
General hashtags: #ml #dl #ai #nlp

@data_science_weekly

Linear Algebra Review and Reference by Zico Kolter (updated by Chuong Do and Tengyu Ma)

Just read the book!

Links:
• Linear Algebra Review and Reference
• Probability Theory Review and Reference

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #linearalgebra #math #mathematics #algebra

@data_science_weekly

ML Design Doc by Eugene Yan

A template for design docs for machine learning systems based on this post.

Note: This template is a guideline / checklist and is not meant to be exhaustive. The intent of the design doc is to help you think better (about the problem and design) and get feedback. Adopt whichever sections—and add new sections—to meet this goal. View other templates, examples here.

Link: GitHub

Navigational hashtags: #armknowledgesharing #armrepo
General hashtags: #mlsysdes #mlsystemdesign #mlsd

@data_science_weekly

Practical RL

An open course on reinforcement learning in the wild. Taught on-campus at HSE and YSDA and maintained to be friendly to online students (both English and Russian).

Manifesto:
• Optimize for the curious. For all the materials that aren’t covered in detail there are links to more information and related materials (D.Silver/Sutton/blogs/whatever). Assignments will have bonus sections if you want to dig deeper.
• Practicality first. Everything essential to solving reinforcement learning problems is worth mentioning. We won't shun away from covering tricks and heuristics. For every major idea there should be a lab that makes you to “feel” it on a practical problem.
• Git-course. Know a way to make the course better? Noticed a typo in a formula? Found a useful link? Made the code more readable? Made a version for alternative framework? You're awesome! Pull-request it!

Link: GitHub

Navigational hashtags: #armknowledgesharing #armcourses
General hashtags: #rl #reinforcementlearning

@data_science_weekly

Clean Machine Learning Code by Moussa Taifi

This book explores the hidden fragility and complexity behind real-world machine learning systems. It examines how highly skilled data scientists and ML practitioners often struggle when their models become part of production software, where fragile code, complex dependencies, and poor engineering practices can lead to instability and failure.

Drawing parallels between today’s machine learning boom and earlier eras of software engineering, the book argues that many challenges in ML systems are not entirely new but echoes of long-standing software problems. It highlights the risks posed by overly complex and opaque ML software—especially in a fast-growing field with many inexperienced practitioners—and emphasizes the real-world consequences of unreliable systems.

Ultimately, the book advocates for applying proven software engineering principles to machine learning, offering a path toward building more robust, maintainable, and trustworthy ML systems.

Link: Book

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #ml #machinelearning #cleancode

@data_science_weekly

CS50’s Introduction to Databases with SQL

This is CS50’s introduction to databases using a language called SQL.

• Learn how to create, read, update, and delete data with relational databases, which store data in rows and columns.
• Learn how to model real-world entities and relationships among them using tables with appropriate types, triggers, and constraints.
• Learn how to normalize data to eliminate redundancies and reduce potential for errors.
• Learn how to join tables together using primary and foreign keys.
• Learn how to automate searches with views and expedite searches with indexes.
• Learn how to connect SQL with other languages like Python and Java.

Course begins with SQLite for portability’s sake and ends with introductions to PostgreSQL and MySQL for scalability’s sake as well. Assignments inspired by real-world datasets.

Whereas CS50x itself focuses on computer science more generally as well as programming with C, Python, SQL, and JavaScript, this course, aka CS50 SQL, is entirely focused on SQL. You can take CS50 SQL before CS50x, during CS50x, or after CS50x. But for an introduction to computer science itself, you should still take CS50x!

Links:
• Site
• Lectures (YouTube Playlist)

Navigational hashtags: #armknowledgesharing #armcourses
General hashtags: #sql

@data_science_weekly

Elements of Programming Interviews in Python: The Insiders' Guide by Adnan Aziz, Tsung-Hsien Lee and Amit Prakash

EPI is your comprehensive guide to interviewing for software development roles.

The core of EPI is a collection of over 250 problems with detailed solutions. The problems are representative of interview questions asked at leading software companies. The problems are illustrated with 200 figures, 300 tested programs, and 150 additional variants.

The book begins with a summary of the nontechnical aspects of interviewing, such as strategies for a great interview, common mistakes, perspectives from the other side of the table, tips on negotiating the best offer, and a guide to the best ways to use EPI. We also provide a summary of data structures, algorithms, and problem solving patterns.

Coding problems are presented through a series of chapters on basic and advanced data structures, searching, sorting, algorithm design principles, and concurrency. Each chapter stars with a brief introduction, a case study, top tips, and a review of the most important library methods. This is followed by a broad and thought-provoking set of problems.

Links:
• Amazon
• Free Sample

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #programming #python #algorithms #datastructures #interviewpreparation #interviewprep #interview

@data_science_weekly

Build a Large Language Model by Sebastian Raschka

In Build a Large Language Model (from Scratch) bestselling author Sebastian Raschka guides you step by step through creating your own LLM. Each stage is explained with clear text, diagrams, and examples. You’ll go from the initial design and creation, to pretraining on a general corpus, and on to fine-tuning for specific tasks.

Build a Large Language Model (from Scratch) teaches you how to:

• Plan and code all the parts of an LLM
• Prepare a dataset suitable for LLM training
• Fine-tune LLMs for text classification and with your own data
• Use human feedback to ensure your LLM follows instructions
• Load pretrained weights into an LLM

Build a Large Language Model (from Scratch) takes you inside the AI black box to tinker with the internal systems that power generative AI. As you work through each key stage of LLM creation, you’ll develop an in-depth understanding of how LLMs work, their limitations, and their customization methods. Your LLM can be developed on an ordinary laptop, and used as your own personal assistant.

Links:
• Amazon
• GitHub

Navigational hashtags: #armknowledgesharing #armbooks
General hashtags: #llm #largelanguagemodels #nlp #naturallanguageprocessing

@data_science_weekly

Engineering Math: Differential Equations and Dynamical Systems by Steve Brunton

This series presents a comprehensive introduction and overview to Differential Equations & Dynamical Systems. Dynamical systems are differential equations that describe any system that changes in time. Applications include fluid dynamics, elasticity and vibrations, weather and climate systems, epidemiology, biomechanics, space mission design, and control theory.

Author assumes that students have taken some calculus (but might not remember it) and are interested in modeling the real world.

Link: YouTube

Navigational hashtags: #armknowledgesharing #armcourse
General hashtags: #math #mathematics

@data_science_weekly

Machine Learning Design Primer

Some helpful notes for Machine Learning System Design Interview preparation, which author gathered from various resources to prepare for machine learning systems design interview.

Link: GitHub

Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #interview #techinterview #interviewprep #interviewpreparation #mlsd #mlsystemdesign #mlsysdes #systemdesign

@data_science_weekly

A/B Testing & Experimentation Roadmap

This roadmap is for analysts, data scientists, and product folks who want to go from “I know what an A/B test is” to running trustworthy, advanced online experiments (CUPED, sequential testing, quasi-experiments, Bayesian, etc.).

It’s organized by topics. You don’t have to go strictly top-to-bottom, but earlier sections are foundations for later ones.

Link: GitHub

Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #statistics #abtesting #ab

@data_science_weekly

Tech Interview Cheat Sheet

This list is meant to be both a quick guide and reference for further research into these topics. It's basically a summary of that comp sci course you never took or forgot about, so there's no way it can cover everything in depth.

Link: Site

Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #interview #techinterview #interviewprep #interviewpreparation

@data_science_weekly

Summary of the year for the channel "Artem Ryblov’s Data Science Weekly" from @TGStat

Happy New Year!

Deep Learning Tuning Playbook by Google

This document helps you train deep learning models more effectively. Although this document emphasizes hyperparameter tuning, it also touches on other aspects of deep learning training, such as training pipeline implementation and optimization.

This document assumes your machine learning task is either a supervised learning problem or a similar problem (for example, self-supervised learning) That said, some of the advice in this document may also apply to other types of machine learning problems.

Links:
- GitHub
- Site

Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #dl #deeplearning #google

@data_science_weekly

PyTorch internals

This talk is for those of you who have used PyTorch, and thought to yourself, "It would be great if I could contribute to PyTorch," but were scared by PyTorch's behemoth of a C++ codebase. I'm not going to lie: the PyTorch codebase can be a bit overwhelming at times. The purpose of this talk is to put a map in your hands: to tell you about the basic conceptual structure of a "tensor library that supports automatic differentiation", and give you some tools and tricks for finding your way around the codebase. I'm going to assume that you've written some PyTorch before, but haven't necessarily delved deeper into how a machine learning library is written.

The talk is in two parts: in the first part, I'm going to first introduce you to the conceptual universe of a tensor library. I'll start by talking about the tensor data type you know and love, and give a more detailed discussion about what exactly this data type provides, which will lead us to a better understanding of how it is actually implemented under the hood. If you're an advanced user of PyTorch, you'll be familiar with most of this material. We'll also talk about the trinity of "extension points", layout, device and dtype, which guide how we think about extensions to the tensor class. In the live talk at PyTorch NYC, I skipped the slides about autograd, but I'll talk a little bit about them in these notes as well.

The second part grapples with the actual nitty gritty details involved with actually coding in PyTorch. I'll tell you how to cut your way through swaths of autograd code, what code actually matters and what is legacy, and also all of the cool tools that PyTorch gives you for writing kernels.

Link: Site

Navigational hashtags: #armknowledgesharing #armtutorials
General hashtags: #dl #deeplearning #pytorch

@data_science_weekly