Deep learning architectures: A mathematical approach
Document Type
Book
Publication Date
2020
Department/School
Mathematics
Abstract
This book describes how neural networks operate from the mathematical point of view. As a result, neural networks can be interpreted both as function universal approximators and information processors. The book bridges the gap between ideas and concepts of neural networks, which are used nowadays at an intuitive level, and the precise modern mathematical language, presenting the best practices of the former and enjoying the robustness and elegance of the latter.
Link to WorldCat Entry
Recommended Citation
Calin, O. (2020). Deep learning architectures: A mathematical approach. Springer International. https://doi.org/10.1007/978-3-030-36721-3
Comments
O. Calin is a faculty member in EMU's Department of Mathematics and Statistics.
This book was featured at EMU's 2020 Faculty Scholarly and Creative Activity Showcase.