A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to the uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition. The term "recurrent neural network" is used to refer to the class of networks with an infinite impulse response, whereas "convolutional neural network" refers to the class of finite impulse response. Both classes of networks exhibit temporal dynamic behavior. A finite impulse recurrent network is a directed acyclic graph that can be unrolled and replaced with a strictly feedforward neural network, while an infinite impulse recurrent network is a directed cyclic graph that can not be unrolled.
Nonlinear control theory is the area of control theory which deals with systems that are nonlinear, time-variant, or both. Control theory is an interdisciplinary branch of engineering and mathematics that is concerned with the behavior of dynamical systems with inputs, and how to modify the output by changes in the input using feedback, feedforward, or signal filtering. The system to be controlled is called the "plant". One way to make the output of a system follow a desired reference signal is to compare the output of the plant to the desired output, and provide feedback to the plant to modify the output to bring it closer to the desired output.
Petar V. Kokotovic is professor emeritus in the College of Engineering at the University of California, Santa Barbara, USA. He has made contributions in the areas of adaptive control, singular perturbation techniques, and nonlinear control especially the backstepping stabilization method.
An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. The connectivity and weights of hidden neurons are fixed and randomly assigned. The weights of output neurons can be learned so that the network can produce or reproduce specific temporal patterns. The main interest of this network is that although its behavior is non-linear, the only weights that are modified during training are for the synapses that connect the hidden neurons to output neurons. Thus, the error function is quadratic with respect to the parameter vector and can be differentiated easily to a linear system.
In control theory, a separation principle, more formally known as a principle of separation of estimation and control, states that under some assumptions the problem of designing an optimal feedback controller for a stochastic system can be solved by designing an optimal observer for the state of the system, which feeds into an optimal deterministic controller for the system. Thus the problem can be broken into two separate parts, which facilitates the design.
Kumpati S. Narendra is an American control theorist, who currently holds the Harold W. Cheel Professorship of Electrical Engineering at Yale University. He received the Richard E. Bellman Control Heritage Award in 2003. He is noted "for pioneering contributions to stability theory, adaptive and learning systems theory". He is also well recognized for his research work towards learning including Neural Networks and Learning Automata.
George Zames was a Polish-Canadian control theorist and professor at McGill University, Montreal, Quebec, Canada. Zames is known for his fundamental contributions to the theory of robust control, and was credited for the development of various well-known results such as small-gain theorem, passivity theorem, circle criterion in input–output form, and most famously, H-infinity methods.
Miroslav Krstić is an American control theorist and Distinguished Professor of Mechanical and Aerospace Engineering at the University of California, San Diego (UCSD). Krstić is also the director of the Center for Control Systems and Dynamics at UCSD and a Senior Associate Vice Chancellor for Research. In the list of eminent researchers in systems and control, he is the youngest.
Jeff S. Shamma is an American control theorist. He is the Department Head and Professor of Industrial and Enterprise Systems Engineering at the University of Illinois Urbana-Champaign. Formerly, he was a Professor of Electrical engineering at the King Abdullah University of Science and Technology. Before that, he held the Julian T. Hightower Chair in Systems & Control Systems and Controls at the Georgia Institute of Technology. He is known for his early work in nonlinear and adaptive control, particularly on gain scheduling, robust control, and more recently, distributed systems.
Preflexes are the latent capacities in the musculoskeletal system that auto-stabilize movements through the use of the nonlinear visco-elastic properties of muscles when they contract. The term "preflex" for such a zero-delay, intrinsic feedback loop was coined by Loeb. Unlike stabilization methods using neurons, such as reflexes and higher brain control, a preflex happens with minimal time delay; however, it only stabilizes the main movements of the musculoskeletal system.
A networked control system (NCS) is a control system wherein the control loops are closed through a communication network. The defining feature of an NCS is that control and feedback signals are exchanged among the system's components in the form of information packages through a network.
Dragoslav D. Šiljak is professor emeritus of Electrical Engineering at Santa Clara University, where he held the title of Benjamin and Mae Swig University Professor. He is best known for developing the mathematical theory and methods for control of complex dynamic systems characterized by large-scale, information structure constraints and uncertainty.
Active disturbance rejection control is a model-free control technique used for designing controllers for systems with unknown dynamics and external disturbances. This approach only necessitates an estimated representation of the system's behavior to design controllers that effectively counteract disturbances without causing any overshooting.
Wassim Michael Haddad is a Lebanese-Greek-American applied mathematician, scientist, and engineer, with research specialization in the areas of dynamical systems and control. His research has led to fundamental breakthroughs in applied mathematics, thermodynamics, stability theory, robust control, dynamical system theory, and neuroscience. Professor Haddad is a member of the faculty of the School of Aerospace Engineering at Georgia Institute of Technology, where he holds the rank of Professor and Chair of the Flight Mechanics and Control Discipline. Dr. Haddad is a member of the Academy of Nonlinear SciencesArchived 2016-03-04 at the Wayback Machine for recognition of paramount contributions to the fields of nonlinear stability theory, nonlinear dynamical systems, and nonlinear control and an IEEE Fellow for contributions to robust, nonlinear, and hybrid control systems.
Arthur James Krener is an American mathematician. He is a distinguished visiting professor in the department of applied mathematics at the Naval Postgraduate School. He has made contributions in the areas of control theory, nonlinear control, and stochastic processes.
Karl Henrik Johansson is a Swedish researcher and best known for his pioneering contributions to networked control systems, cyber-physical systems, and hybrid systems. His research has had particular application impact in transportation, automation, and energy networks. He holds a Chaired Professorship in Networked Control at the KTH Royal Institute of Technology in Stockholm, Sweden. He is Director of KTH Digital Futures.
Daniel M. Liberzon is the Richard T. Cheng Professor of Electrical and Computer Engineering at the University of Illinois at Urbana–Champaign.
Frank L. Lewis is an American electrical engineer, academic and researcher. He is a professor of electrical engineering, Moncrief-O’Donnell Endowed Chair, and head of Advanced Controls and Sensors Group at The University of Texas at Arlington (UTA). He is a member of UTA Academy of Distinguished Teachers and a charter member of UTA Academy of Distinguished Scholars.
Maamar Bettayeb is a control theorist, educator and inventor. He is the author of publications on understanding the singular value decomposition and model order reduction. Bettayeb is also a promoter of scientific research.
Saverio Mascolo is an Italian information engineer, academic and researcher. He is the former Head of the Department of Electrical Engineering and Information Science and the professor of Automatic Control at Department of Ingegneria Elettrica e dell'Informazione (DEI) at Politecnico di Bari, Italy.
