https://axon.cs.byu.edu/~martinez/classes/678/Presentations/Yao.pdf

Extreme learning machine: Theory and applications

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word "reinforcement." The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

/pdf/reinforcement-learning-a-survey-38lmyylg2y.pdf

Reinforcement learning: a survey

Planning algorithms are impacting technical disciplines and industries around the world, including robotics, computer-aided design, manufacturing, computer graphics, aerospace applications, drug design, and protein folding. This coherent and comprehensive book unifies material from several sources, including robotics, control theory, artificial intelligence, and algorithms. The treatment is centered on robot motion planning but integrates material on planning in discrete spaces. A major part of the book is devoted to planning under uncertainty, including decision theory, Markov decision processes, and information spaces, which are the “configuration spaces” of all sensor-based planning problems. The last part of the book delves into planning under differential constraints that arise when automating the motions of virtually any mechanical system. Developed from courses taught by the author, the book is intended for students, engineers, and researchers in robotics, artificial intelligence, and control theory as well as computer graphics, algorithms, and computational biology.

Planning Algorithms: Introductory Material

This paper surveys the field of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the field and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but differs considerably in the details and in the use of the word ``reinforcement.'' The paper discusses central issues of reinforcement learning, including trading off exploration and exploitation, establishing the foundations of the field via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.

Reinforcement Learning: A Survey

A simple numerical procedure for estimating the stochastic robustness of a linear, time-invariant system is described. Based on Monte Carlo evaluation of the system's eigenvalues, this analysis approach introduces the probability of instability as a scalar measure of stability robustness. The related stochastic root locus, a portrayal of the root probability density, provides insight into robustness characteristics. Parameter uncertainties are not limited to Gaussian distributions; non-Gaussian cases, including uncertain-but-bounded variations, can be considered as well. Confidence intervals for the scalar probability of instability address computational issues inherent in Monte Carlo simulation. An example demonstrates stochastic robustness as applied to a physical system with Gaussian, uniformly distributed, and binary parameters.

Multivariate Histograms for Analysis of Linear Control System Robustness

The threat of low-altitude wind shear has prompted development of aircraft-based sensors that measure winds directly on the aircraft's intended flight path Measurements from these devices are subject to turbulence inputs and measurement error, as well as to the underlying wind profile Stochastic estimators are developed to process on-board Doppler sensor measurements, producing optimal estimates of the winds along the path A stochastic prediction technique is described to predict the hazard to the aircraft from the estimates as well as the level of uncertainty of the hazard prediction The stochastic prediction technique is demonstrated in a simulated microburst wind shear environment Use of the technique in a decision-making process is discussed >

Stochastic prediction techniques for wind shear hazard assessment

A control-theoretic pilot model is incorporated in the analysis of pilot-aircraft motions during maneuvers. The pilot model is found to be of value for the definition of maneuvering flight stabililty boundaries, and it simulates pilot control actions during a representative task with reasonable fidelity. The model also is used to demonstrate the consequences of improperly adapted pilot response strategy. It is concluded that the pilot model presented here provides important capabilities for evaluation of flying qualities and for identifying proper piloting procedures during difficult maneuvers.

Stability of the pilot-aircraft system in maneuvering flight

A rule-based paradigm for intelligent adaptive flight control

The threat of low-altitude wind shear has prompted development of aircraft-based sensors that measure winds directly on the aircraft's intended flight path. Measurements from these devices are subject to turbulence inputs and measurement error, as well as to the underlying wind profile. Stochastic estimators are developed to process on-board Doppler sensor measurements, producing optimal estimates of the winds along the path. A stochastic prediction technique is described to predict the hazard to the aircraft from the estimates as well as the level of uncertainty of the hazard prediction. The stochastic prediction technique is demonstrated in a simulated microburst wind shear environment. Use of the technique in a decision-making process is discussed. >

Robert F. Stengel

Papers

Multivariate Histograms for Analysis of Linear Control System Robustness

Stochastic prediction techniques for wind shear hazard assessment

Stability of the pilot-aircraft system in maneuvering flight

A rule-based paradigm for intelligent adaptive flight control

Stochastic prediction techniques for wind shear hazard assessment