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

For pt. I see ibid., vol. 4 (1993). This paper considers the problems of regulation and tracking of a dynamical system when the state variables of the dynamical system are not accessible. The existence of the nonlinear maps describing the identifier and controller are first established and the implications for neural network realizations are described. Simulation results are included to complement the theoretical discussions.

Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control

Identification and control when plant output is corrupted with disturbance and when plant parameters vary with time are considered. It is shown how the error model can be described by a non-homogeneous differential equation. Subject to bounded disturbance and parameter variation and sufficiently rich input the parameter error vector remains bounded and explicit bounds are derived. For inputs that are not sufficiently rich some sufficient conditions for stability and some examples of instability are given. Finally, a non-linear adaptation algorithm is presented for the control problem that insures the boundedness of the parameter error vector and all signals in the system.

Bounded error adaptive control

An attempt is made to indicate how practically viable controllers can be designed using neural networks, based on results in nonlinear control theory. The problem of stabilization of a dynamical system around an equilibrium point when the state of the system is accessible is considered. Simulation results are included to complement the theoretical discussions. >

Control of nonlinear dynamical systems using neural networks: controllability and stabilization

A new adaptive law motivated by that given in [1] is proposed for the robust adaptive control of plants with unknown parameters. In this adaptive law the output error e l plays a dual role in the adjustment of the control parameter vector. In the ideal case the adaptive system has bounded solutions; in addition the error equations are uniformly asymptotically stable in the large when the reference input is sufficiently persistently exciting. The adaptive system is also shown to be robust under bounded external disturbances. Finally it is shown that, by suitably modifying the adaptive law, the overall system can be made robust in the presence of unmodeled dynamics of the plant.

Kumpati S. Narendra

Papers

Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control

Bounded error adaptive control

Control of nonlinear dynamical systems using neural networks: controllability and stabilization

A New Adaptive Law for Robust Adaptation without Persistent Excitation

Adaptation and learning in automatic systems