Deep Learning Architectures: A Mathematical Approach (Springer Series in the Data Sciences)
by Ovidiu Calin
Deep Learning Architectures: A Mathematical Approach explores the structures of deep learning from a mathematical perspective. As part of Springer’s Data Sciences series, the book offers a formal treatment for readers studying deep learning architectures, mathematics, computer science, and related data science topics.
About This Book
Deep Learning Architectures: A Mathematical Approach presents deep learning through a mathematical lens.
The book focuses on architectures used in deep learning and their underlying formal structures.
Its treatment is positioned within the broader field of data science.
Published as part of the Springer Series in the Data Sciences, it may appeal to readers interested in rigorous study of deep learning.
Reviews
No reviews yet. Be the first to review this book!