Deep Neural Networks WASD Neuronet Models, Algorithms, and Applications

Toward Deep Neural Networks: WASD Neuronet Models, Algorithms, and Applications introduces the outlook and extension toward deep neural networks, with a focus on the weights-and-structure determination (WASD) algorithm. Based on the authors’ 20 years of research experience on neuronets, the book explores the models, algorithms, and applications of the WASD neuronet, and allows reader to extend the techniques in the book to solve scientific and engineering problems. The book will be of interest to engineers, senior undergraduates, postgraduates, and researchers in the fields of neuronets, computer mathematics, computer science, artificial intelligence, numerical algorithms, optimization, simulation and modeling, deep learning, and data mining. Features Focuses on neuronet models, algorithms, and applications Designs, constructs, develops, analyzes, simulates and compares various WASD neuronet models, such as single-input WASD neuronet models, two-input WASD neuronet models, three-input WASD neuronet models, and general multi-input WASD neuronet models for function data approximations Includes real-world applications, such as population prediction Provides complete mathematical foundations, such as Weierstrass approximation, Bernstein polynomial approximation, Taylor polynomial approximation, and multivariate function approximation, exploring the close integration of mathematics (i.e., function approximation theories) and computers (e.g., computer algorithms) Utilizes the authors' 20 years of research on neuronets

I Single-Input-Single-Output Neuronet 1 Single-Input Euler-PolynomialWASD Neuronet 2 Single-Input Bernoulli-PolynomialWASD Neuronet 3 Single-Input Laguerre-PolynomialWASD Neuronet II Two-Input-Single-Output Neuronet 4 Two-Input Legendre-PolynomialWASD Neuronet 5 Two-Input Chebyshev-Polynomial-of-Class-1WASD Neuronet 6 Two-Input Chebyshev-Polynomial-of-Class-2WASD Neuronet III Three-Input-Single-Output Neuronet 7 Three-Input Euler-PolynomialWASD Neuronet 8 Three-Input Power-ActivationWASD Neuronet IV General Multi-Input Neuronet 9 Multi-Input Euler-PolynomialWASD Neuronet 10 Multi-Input Bernoulli-PolynomialWASD Neuronet 11 Multi-Input Hermite-PolynomialWASD Neuronet 12 Multi-Input Sine-ActivationWASD Neuronet V Population Applications Using Chebyshev-Activation Neuronet 13 Application to Asian Population Prediction 14 Application to European Population Prediction 15 Application to Oceania Population Prediction 16 Application to Northern American Population Prediction 17 Application to Indian Subcontinent Population Prediction 18 Application toWorld Population Prediction VI Population Applications Using Power-Activation Neuronet 19 Application to Russian Population Prediction 20 WASD Neuronet versus BP Neuronet Applied to Russia Population Prediction 21 Application to Chinese Population Prediction 22 WASD Neuronet versus BP Neuronet Applied to Chinese Population Prediction VII Other Applications 23 Application to USPD Prediction 24 Application to Time Series Prediction 25 Application to GFR Estimation

Yunong Zhang receiveda BSc. degree from Huazhong University of Science and Technology, Wuhan, China, in 1996,an MSc. degree from South China University of Technology, Guangzhou, China, in 1999, anda PhD. degree from Chinese University of Hong Kong, Shatin, Hong Kong, China, in 2003. He is currently a professor at the School of Information Science and Technology, Sun Yat-sen University, Guangzhou, China. Yunong Zhang was supported by the Program for New Century Excellent Talents in Universities in 2007, was presented the Best Paper Award of ISSCAA in 2008 and the Best Paper Award of ICAL in 2011, and was among the Highly Cited Scholars of China selected and published by Elsevier from year 2014 to year 2017. His web-page is now available at http://sdcs.sysu.edu.cn/content/2477. Dechao Chen receiveda BSc. degree from Guangdong University of Technology, Guangzhou, China, in 2013. He is currently pursuing his PhD. degree in Communication and Information Systems at School of Information Science and Technology, Sun Yat-sen University, Guangzhou, China, under the direction of Professor Yunong Zhang. His research interests include robotics, neuronets, and nonlinear dynamics systems. Chengxu Ye receiveda BSc. degree from Shanxi Normal University, Xian, China, in 1991,an MSc. degree from Qinghai Normal University, Xining, China, in 2008, anda PhD. degree from Sun Yat-sen University, Guangzhou, China, in 2015. He is currently a professor at School of Computer, Qinghai Normal University, Xining, China. His main research interests include machine learning, neuronets, computation and optimization. He has published over 30 scientific papers in journals and conferences.