Deep Learning Classifiers with Memristive Networks_ Theory and Applications_Alex Pappachen James.pdf

Modeling and Optimization in Science and Technologies Alex Pappachen James    Editor Deep Learning Classifiers with Memristive Networks Theory and Applications Modeling and Optimization in Science and Technologies Volume 14 Series Editors Srikanta Patnaik, SOA University, Bhubaneswar, India e-mail:[email protected] Ishwar K. Sethi, Oakland University, Rochester, USA e-mail:[email protected] Xiaolong Li, Indiana State University, Terre Haute, USA e-mail:[email protected] Editorial Board Li Cheng, The Hong Kong Polytechnic University, Hong Kong Jeng-Haur Horng, National Formosa University, Yulin, Taiwan Pedro U. Lima, Institute for Systems and Robotics, Lisbon, Portugal Mun-Kew Leong, Institute of Systems Science, National University of Singapore, Singapore Muhammad Nur, Diponegoro University, Semarang, Indonesia Luca Oneto, University of Genoa, Italy Kay Chen Tan, National University of Singapore, Singapore Sarma Yadavalli, University of Pretoria, South Africa Yeon-Mo Yang, Kumoh National Institute of Technology, Gumi, Korea (Republic of) Liangchi Zhang, The University of New South Wales, Australia Baojiang Zhong, Soochow University, Suzhou, China Ahmed Zobaa, Brunel University, Uxbridge, Middlesex, UK The book series Modeling and Optimization in Science and Technologies (MOST) publishes basic principles as well as novel theories and methods in the fast-evolving field of modeling and optimization. Topics of interest include, but are not limited to: methods for analysis, design and control of complex systems, networks and machines; methods for analysis, visualization and management of large data sets; use of supercomputers for modeling complex systems; digital signal processing; molecular modeling; and tools and software solutions for different scientific and technological purposes. Special emphasis is given to publications discussing novel theories and practical solutions that, by overcoming the limitations of traditional methods, may successfu