Machine learning : theory to applications / Seyedeh Leili Mirtaheri, Assistant Professor, Electrical and Computer Engineering Department, Kharazmi University, Tehran, Reza Shahbazian, Department of Mathematics and Computer Science, University of Calabria, Italy.
Material type: TextPublication details: New York CRC Press 2022Edition: First editionDescription: ix, 201 pages : illustrations (some color) ; 24 cmISBN:- 9780367634568
- 006.31 23 MIR-M 2022 790204
Item type | Current library | Collection | Call number | Copy number | Status | Date due | Barcode | Item holds | |
---|---|---|---|---|---|---|---|---|---|
Reference | Faculty of CS & IT Library Book Cart | Book | 006.31 MIR-M 2022 790204 (Browse shelf(Opens below)) | 1 | Not For Loan (Restricted Access) | 790204 | |||
Books | Faculty of CS & IT Library Book Cart | Book | 006.31 MIR-M 2022 790205 (Browse shelf(Opens below)) | 2 | Available | 790205 | |||
Books | Faculty of CS & IT Library Book Cart | Book | 006.31 MIR-M 2022 790206 (Browse shelf(Opens below)) | 3 | Available | 790206 |
Includes bibliographical references and index.
"Machine learning is an application of artificial intelligence that focuses on the development of computer-based programs that can access data and use it to learn for themselves. In this book, we present the basics of machine learning including the four unsupervised, semi-supervised, self- supervised and reinforcement learning. In recent years, neural networks have appeared in many applications with deep learning concepts. In this book, we review the theory of different deep learning techniques including convolutional, recurrent and feed-forward neural networks. This book also provides the reader with a guided tour of needed tools and evaluation techniques in Python that helps the reader to understand the applications of machine learning techniques. The key feature of this book is its focus on recent applications of machine learning and deep learning techniques that benefit from new ideas including generative networks to pre-process the data set or to produce the synthetic data for reducing the actual data-set sizes or improving the performance. We also present the different models of generative adversarial networks and their advantages on applications such as image processing, new communication networks, cognitive science, security and signal processing"--