Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Gradient-based learning applied to document recognition

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

The architecture and learning procedure underlying ANFIS (adaptive-network-based fuzzy inference system) is presented, which is a fuzzy inference system implemented in the framework of adaptive networks. By using a hybrid learning procedure, the proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In the simulation, the ANFIS architecture is employed to model nonlinear functions, identify nonlinear components on-line in a control system, and predict a chaotic time series, all yielding remarkable results. Comparisons with artificial neural networks and earlier work on fuzzy modeling are listed and discussed. Other extensions of the proposed ANFIS and promising applications to automatic control and signal processing are also suggested. >

ANFIS: adaptive-network-based fuzzy inference system

https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

Some of the problems that arise in the control of nonlinear systems in the presence of uncertainty are considered Multilayer neural networks and radial basis function networks are used in the design of identifiers and controllers, and gradient methods are used to adjust their parameters For a restricted class of nonlinear systems, it is shown that globally stable adaptive controllers can be determined Simulation results are presented to demonstrate that the methods presented can be used for the effective control of complex nonlinear systems >

Neural networks in control systems

The model reference adaptive control of a linear plant subjected to bounded disturbances is considered. By analyzing a set of nonlinear differential equations, it is shown that the global behavior of the adaptive system depends upon the persistent excitation of the reference input as well as the amplitude of the external disturbances. The principal contribution of the paper is the derivation of sufficient conditions on the persistent excitation of the reference input, given the maximum amplitude of disturbance, for the signals in the adaptive system to be globally bounded.

Robust adaptive control in the presence of bounded disturbances

The past decade has witnessed a great deal of interest in both the theory and practice of adaptive control using multiple models, switching, and tuning. The general approach was introduced in the early 1990s to cope with large and rapidly varying parameters in control systems. During the following years, detailed mathematical analyses of special classes of systems were carried out. Considerable empirical evidence was also collected to demonstrate the practical viability of the methods proposed. This paper attempts to review critically the stability questions that arise in the study of such systems, describes recent extensions of the approach to non-linear adaptive control, and discuss briefly promising new areas of research, particularly related to the location of models. Copyright © 2003 John Wiley & Sons, Ltd.

Adaptive control using multiple models, switching and tuning

Adaptive control of nonlinear multivariable systems using neural networks

In this note, we define strong and weak common quadratic Lyapunov functions (CQLFs) for sets of linear time-invariant (LTI) systems. We show that the simultaneous existence of a weak CQLF of a special form, and the nonexistence of a strong CQLF, for a pair of LTI systems, is characterized by easily verifiable algebraic conditions. These conditions are found to play an important role in proving the existence of strong CQLFs for general LTI systems.

/pdf/a-result-on-common-quadratic-lyapunov-functions-s00kasoao9.pdf

Kumpati S. Narendra

Papers

Neural networks in control systems

Robust adaptive control in the presence of bounded disturbances

Adaptive control using multiple models, switching and tuning

Adaptive control of nonlinear multivariable systems using neural networks

A result on common quadratic Lyapunov functions