Authors:
- Describes a newer approach to artificial adaptive systems, the auto contractive map
- Offers a comprehensive guide on the use of auto contractive map and its supervised version to extract extensive information from data, lending further meaning to the popular notion of “deep learning”
- Describes how to couple auto contractive maps and graph theoretic methods to organize and understand data in a powerful new way
- Includes numerous examples on real and fictitious data
Part of the book series: Studies in Systems, Decision and Control (SSDC, volume 131)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (8 chapters)
-
Front Matter
About this book
This book offers an introduction to artificial adaptive systems and a general model of the relationships between the data and algorithms used to analyze them. It subsequently describes artificial neural networks as a subclass of artificial adaptive systems, and reports on the backpropagation algorithm, while also identifying an important connection between supervised and unsupervised artificial neural networks.
The book’s primary focus is on the auto contractive map, an unsupervised artificial neural network employing a fixed point method versus traditional energy minimization. This is a powerful tool for understanding, associating and transforming data, as demonstrated in the numerous examples presented here. A supervised version of the auto contracting map is also introduced as an outstanding method for recognizing digits and defects. In closing, the book walks the readers through the theory and examples of how the auto contracting map can be used in conjunction with another artificial neural network, the “spin-net,” as a dynamic form of auto-associative memory.
Keywords
- Associative Memory
- Data Driven Machine Learning
- Fixed Point Theory
- Fuzzy Data Sets
- Graph Theoretic Methods
- Deep Learning
- Auto Associative ANNs
- Adaptive Algorithms
- Spin Network
- Auto-CM Weights Matrix
- Dataset Transformation
- Hybrid Artificial Neural Networks
- Auto-CM Neural Network
- Content Addressable Memory
Authors and Affiliations
-
Semeion Research Center of Sciences of Communication, Rome, Italy
Paolo Massimo Buscema, Giulia Massini, Marco Breda
-
Department of Mathematical and Statistical Sciences, University of Colorado Denver, Denver, USA
Weldon A. Lodwick
-
Department of Radiation Oncology, School of Medicine, University of Colorado Denver, Denver, USA
Francis Newman
-
Physics Department, University of Colorado Denver, Denver, USA
Masoud Asadi-Zeydabadi
Bibliographic Information
Book Title: Artificial Adaptive Systems Using Auto Contractive Maps
Book Subtitle: Theory, Applications and Extensions
Authors: Paolo Massimo Buscema, Giulia Massini, Marco Breda, Weldon A. Lodwick, Francis Newman, Masoud Asadi-Zeydabadi
Series Title: Studies in Systems, Decision and Control
DOI: https://doi.org/10.1007/978-3-319-75049-1
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer International Publishing AG 2018
Hardcover ISBN: 978-3-319-75048-4Published: 06 March 2018
Softcover ISBN: 978-3-030-09135-4Published: 25 December 2018
eBook ISBN: 978-3-319-75049-1Published: 24 February 2018
Series ISSN: 2198-4182
Series E-ISSN: 2198-4190
Edition Number: 1
Number of Pages: VII, 179
Number of Illustrations: 23 b/w illustrations, 74 illustrations in colour
Topics: Computational Intelligence, Data Mining and Knowledge Discovery, Artificial Intelligence, Mathematical Logic and Foundations