Motivation: When running experiments that involve multiple high density oligonucleotide arrays, it is important to remove sources of variation between arrays of non-biological origin. Normalization is a process for reducing this variation. It is common to see non-linear relations between arrays and the standard normalization provided by Affymetrix does not perform well in these situations. Results: We present three methods of performing normalization at the probe intensity level. These methods are called complete data methods because they make use of data from all arrays in an experiment to form the normalizing relation. These algorithms are compared to two methods that make use of a baseline array: a one number scaling based algorithm and a method that uses a non-linear normalizing relation by comparing the variability and bias of an expression measure. Two publicly available datasets are used to carry out the comparisons. The simplest and quickest complete data method is found to perform favorably. Availabilty: Software implementing all three of the complete data normalization methods is available as part of the R package Affy, which is a part of the Bioconductor project http://www.bioconductor.org. Contact: bolstad@stat.berkeley.edu Supplementary information: Additional figures may be found at http://www.stat.berkeley.edu/∼bolstad/normalize/ index.html

http://bmbolstad.com/misc/normalize/bolstad_norm_paper.pdf

A comparison of normalization methods for high density oligonucleotide array data based on variance and bias

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

A new method is presented for flexible regression modeling of high dimensional data. The model takes the form of an expansion in product spline basis functions, where the number of basis functions as well as the parameters associated with each one (product degree and knot locations) are automatically determined by the data. This procedure is motivated by the recursive partitioning approach to regression and shares its attractive properties. Unlike recursive partitioning, however, this method produces continuous models with continuous derivatives. It has more power and flexibility to model relationships that are nearly additive or involve interactions in at most a few variables. In addition, the model can be represented in a form that separately identifies the additive contributions and those associated with the different multivariable interactions.

/pdf/multivariate-adaptive-regression-splines-6d1qoagxfb.pdf

Multivariate Adaptive Regression Splines

Monte Carlo methods are revolutionizing the on-line analysis of data in fields as diverse as financial modeling, target tracking and computer vision. These methods, appearing under the names of bootstrap filters, condensation, optimal Monte Carlo filters, particle filters and survival of the fittest, have made it possible to solve numerically many complex, non-standard problems that were previously intractable. This book presents the first comprehensive treatment of these techniques, including convergence results and applications to tracking, guidance, automated target recognition, aircraft navigation, robot navigation, econometrics, financial modeling, neural networks, optimal control, optimal filtering, communications, reinforcement learning, signal enhancement, model averaging and selection, computer vision, semiconductor design, population biology, dynamic Bayesian networks, and time series analysis. This will be of great value to students, researchers and practitioners, who have some basic knowledge of probability. Arnaud Doucet received the Ph. D. degree from the University of Paris-XI Orsay in 1997. From 1998 to 2000, he conducted research at the Signal Processing Group of Cambridge University, UK. He is currently an assistant professor at the Department of Electrical Engineering of Melbourne University, Australia. His research interests include Bayesian statistics, dynamic models and Monte Carlo methods. Nando de Freitas obtained a Ph.D. degree in information engineering from Cambridge University in 1999. He is presently a research associate with the artificial intelligence group of the University of California at Berkeley. His main research interests are in Bayesian statistics and the application of on-line and batch Monte Carlo methods to machine learning. Neil Gordon obtained a Ph.D. in Statistics from Imperial College, University of London in 1993. He is with the Pattern and Information Processing group at the Defence Evaluation and Research Agency in the United Kingdom. His research interests are in time series, statistical data analysis, and pattern recognition with a particular emphasis on target tracking and missile guidance.

/pdf/sequential-monte-carlo-methods-in-practice-3kfxeebn8e.pdf

Sequential Monte Carlo methods in practice

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

Locally weighted regression, or loess, is a way of estimating a regression surface through a multivariate smoothing procedure, fitting a function of the independent variables locally and in a moving fashion analogous to how a moving average is computed for a time series With local fitting we can estimate a much wider class of regression surfaces than with the usual classes of parametric functions, such as polynomials The goal of this article is to show, through applications, how loess can be used for three purposes: data exploration, diagnostic checking of parametric models, and providing a nonparametric regression surface Along the way, the following methodology is introduced: (a) a multivariate smoothing procedure that is an extension of univariate locally weighted regression; (b) statistical procedures that are analogous to those used in the least-squares fitting of parametric functions; (c) several graphical methods that are useful tools for understanding loess estimates and checking the a

https://www.stat.washington.edu/courses/stat527/s14/readings/Cleveland_Delvin_JASA_1988.pdf

Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting

Regression by local fitting: Methods, properties, and computational algorithms

The difficulty of expressing database queries was examined as a function of the language used. Two distinctly different query methods were investigated. One used a standard database query language, SQL, requiring users to express an English query using a formal syntax and appropriate combinations of boolean operators. The second used a newly designed Truth-table Exemplar-Based Interface (TEBI), which only required subjects to be able to choose examplars from a system-generated table representing a sample database. Through users' choices of critical exemplars, the system could distinguish between interpretations of an otherwise ambiguous English query. Performance was measured by number correct, time to complete queries, and confidence in query correctness. Individual difference analyses were done to examine the relationship between subjects' characteristics and ability to express database queries. Subjects' performance was observed to be both better, and more resistant to variability in age and levels of cognitive skills, when using TEBI than when using SQL to specify queries. Possible reasons for these differences are discussed.

No IFs, ANDs, or ORs: a study of databases querying

Two distinctly different methods of expressing database queries were compared to evaluate differences in their difficulty. One method was a standard database query language, SQL, while the second method only required subjects to be able to make use of tables representing sample databases. Clear differences emerged in subject performance. Regression techniques demonstrated an association between performance and a set of cognitive skills.

A Cognitive Analysis of Database Query Production

The distribution of members of the American Statistical Association (ASA) by several demographic and professional measures is characterized. The analysis is based on a 1979 survey of ASA members who resided in the U.S. More detailed analysis focuses on how demographic and professional characteristics affect the distribution of income and the odds of participating in ASA activities. Several interesting observations are made. Years of experience since highest degree is the most important predictor of income. Highest degree and whether employed in academia are also important. There is a significant difference between the distribution of income for men and women; although the difference is insignificant at one year of experience, it increases with the experience level. Although the survey represented a 100% sample of blacks, Hispanics, and native Americans in the ASA, there is insufficient data to formulate a detailed model of income for this minority group; its average income, however, falls below t...

Susan J. Devlin

Papers

Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting

Regression by local fitting: Methods, properties, and computational algorithms

No IFs, ANDs, or ORs: a study of databases querying

A Cognitive Analysis of Database Query Production

A Characterization of 1979 ASA Members