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

Direct, Indirect and Combined Methods of Adaptive Control are used for the robust adaptive control of a first order plant with increasing levels of uncertainty. The latter include external disturbances, time delays, unmodeled dynamics and sensor noise.

Robust Adaptive Control using Direct and Indirect Methods

A mathematical framework is setup for considering problems related to regulation and tracking in nonlinear systems. The conditions are expressed in terms of the linearization of the nonlinear systems. The treatment permits a relatively straightforward extension of known results in the linear case to the corresponding nonlinear problems.

Identification and control of a nonlinear dynamical system /spl Sigma/ based on its linearization /spl Sigma//sub L/. I

: A gradient method is presented for adjusting the parameters of a system to optimize a performance criterion. The partial derivatives of the performance index with respect to the adjustable parameters are obtained as real time signals, using a single perturbation signal for a system with unknown structure, but favorable topology. Computer simulations are included to indicate the feasibility of the approach. The adaptive control method using a single perturbation signal, as proposed here, has many features in common with the well-known parameter perturbation scheme.

Simultaneous multiple parameter adjustment in adaptive systems using a single perturbation signal

: The paper deals with hybrid adaptive control of single-input single-output linear dynamical systems with unknown parameters. The system operates in continuous time while control parameters updated only at discrete instants. Using a hybrid error model it is shown that adaptive algorithms used in discrete and continuous systems can be directly extended to hybrid systems. The resulting nonlinear time-varying systems are globally stable and independent of the frequency with which the parameters are adjusted.

Kumpati S. Narendra

Papers

Robust Adaptive Control using Direct and Indirect Methods

Identification and control of a nonlinear dynamical system /spl Sigma/ based on its linearization /spl Sigma//sub L/. I

Simultaneous multiple parameter adjustment in adaptive systems using a single perturbation signal

Stable Hybrid Adaptive Control

Analysis of memory depth in fixed structure learning automata