программирование

The Little Learner, Чудесное машинное обучение, Фридман Д.П., Мендхекар А., 2024.
     
   В книге охвачены все концепции, необходимые для интуитивного понимания работы глубоких нейронных сетей, включая тензоры, расширенные операторы, алгоритмы градиентного спуска, искусственные нейроны, полносвязные, сверточные сети и остаточные сети, а также автоматическое дифференцирование. Читатель начнет с азов глубокого обучения и познакомится с полной реализацией полезного приложения: распознавателя зашумленных сигналов азбуки Морзе.
Разговорный стиль, постепенное движение от простого к сложному, забавные иллюстрации, формат вопросов и ответов делают обучение доступным и увлекательным.
Для читателей, знающих математику на уровне средней школы и имеющих некоторый опыт программирования.

The Comprehensive Guide to Machine Learning Algorithms and Techniques, Ahmed M.M., 2024.
     
   This Book provides a comprehensive overview of various machine learning algorithms and techniques, categorized by their primary functions, such as regression, classification, clustering, optimization, and NLP. Each algorithm has been explained in terms of its main concept, purpose, use cases, mathematical background, loss function, pros and cons, and visual representation. This knowledge is crucial for selecting the right algorithm for specific problems and understanding the underlying mechanisms that drive their performance.

Starting Data Analytics with Generative AI and Python, Guja A., Siwiak M., 2025.
     
   This book can be read on three levels, so essentially you have three different books in front of you. At the highest level, it’s a book about data analytics, and you’ll find a basic introduction to the discipline, tools, algorithms, and some more advanced concepts, which together should allow you to perform analytics on your own. It will give you a high-level overview of data analytics as an initial step into the field.

Machine Learning for Tabular Data, Ryan M., Massaron L., 2025.
     
   Machine Learning for Tabular Data dives into a critical area of machine learning: working with tabular data. From the spreadsheets you use every day to the databases that power businesses, tabular data is everywhere. It’s the hidden gem hiding in plain sight. This book goes beyond just theory. It equips you to leverage the power of tabular data by teaching you machine learning techniques specifically designed for it. You’ll learn how to make sense of your data, uncover patterns, and build real-world applications — all with the added benefit of clear and interpretable results.

Reinforcement Learning for Finance, A Python-Based Introductio, Hilpisch Y., 2025.
     
   This book is intended as a concise, Python-based introduction to the major ideas and elements of RL and DQL as applied to finance. It should be useful to both students and academics as well as to practitioners in search of alternatives to existing financial theories and algorithms. The book expects basic knowledge of the Python programming language, object-oriented programming, and the major Python packages used in data science and machine learning, such as NumPy, pandas, matplotlib, scikit-learn, and TensorFlow.

RAG with Python Cookbook ER, Polzer D., 2026.
     
Фрагмент из книги.
In this book, you will often see functions from RAG frameworks like LangChain and LlamaIndex. This makes sense because these RAG frameworks are handy and offer many functions we need to create RAG applications. Nevertheless, check first if you really need them. They are still at an early stage and constantly changing, which can be challenging when deploying apps to production. Since they are merely a collection of more established frameworks, you could also use the standalone frameworks behind LangChain and LlamaIndex.

Python Machine Learning, 100 Exercises.
     
   This book is designed for those who already have a basic understanding of programming and want to dive into Python-based machine learning through hands-on practice.
With 100 targeted exercises, it provides a structured approach to developing and refining your skills. Each exercise includes clear source code and visual output, making it easier to grasp complex concepts.

Математика для Data Science, Нилд Т., 2025.
     
   Освойте математический аппарат, который необходим, чтобы преуспеть в сфере data science, машинного обучения и статистики. Автор книги Томас Нилд поможет вам разобраться в таких дисциплинах, как математический анализ, теория вероятностей, линейная алгебра и статистика, и научиться применять их в контексте таких методов, как линейная регрессия, логистическая регрессия и нейронные сети. Попутно вы узнаете, что представляет собой современная область data science и как использовать полученные знания, чтобы достичь максимального успеха в карьере.