Machine Learning for Computer Scientists and Data Analysts: From an Applied Perspective

This textbook provides an introduction to the theoretical aspects of machine learning (ML) algorithms, including neural networks, generative adversarial networks, and graph convolution networks, with practical implementation examples and assignments. It helps readers understand the concepts and develop skills to choose appropriate ML algorithms for different problem types.

Format: Paperback / softback
Length: 458 pages
Publication date: 10 July 2023
Publisher: Springer Nature Switzerland AG

This comprehensive textbook delves into the intricate realm of machine learning (ML) algorithms, providing a thorough introduction for readers of all levels. Starting from the fundamental principles of neurons, it progresses to complex neural networks, encompassing generative adversarial neural networks and graph convolution networks. By elucidating the core concepts of ML algorithms, this book equips readers with the skills to select the most appropriate ML approach for addressing various problems.

Moreover, the textbook is enriched with numerous case studies, spanning from straightforward time-series forecasting to advanced object recognition and recommender systems utilizing massive databases. These real-world examples not only enhance the theoretical understanding but also provide practical insights into the practical applications of ML.

To further enhance the learning experience, the book includes comprehensive implementation examples and assignments, allowing readers to apply their knowledge and develop their programming skills in ML applications. Whether you are a novice seeking to gain a foundational understanding of ML or an experienced practitioner seeking to expand your expertise, this textbook is an invaluable resource for anyone interested in this rapidly evolving field.

Dimension: 235 x 155 (mm)
ISBN-13: 9783030967581
Edition number: 1st ed. 2022