Sponsored Post.By WhartonSix years ago, Forbes ran an article titled, “Is it possible to collect too much customer data? No!” As the discipline of customer analytics grew, though, minds changed. Earlier this year they ran “Why too much data is a problem and how to prevent it.”

Reinforcement Learning: An Introductionby Rich Sutton and Andrew Barto was recently released on October 15, 2018. The authors were kind enough to put a late draft version of the book online as a PDF. If you are hoping to learn about Reinforcement Learning, this is a great place to start.

In many tasks in machine learning, it is common to want to answer questions given fixed, pre-collected datasets. In some applications, however, we are not given data a priori; instead, we must collect the data we require to answer the questions of interest. This situation arises, for example, in environmental contaminant monitoring and census-style surveys. Collecting the data ourselves allows us to focus our attention on just the most relevant sources of information. However, determining which of these sources of information will yield useful measurements can be difficult. Furthermore, when data is collected by a physical agent (e.g. robot, satellite, human, etc.) we must plan our measurements so as to reduce costs associated with the motion of the agent over time. We call this abstract problem embodied adaptive sensing.

In this Book we argue that the fruitful interaction of computer vision and belief calculus is capable of stimulating significant advances in both fields. From a methodological point of view, novel theoretical results concerning the geometric and algebraic properties of belief functions as mathematical objects are illustrated and discussed in Part II, with a focus on both a perspective ‘geometric approach’ to uncertainty and an algebraic solution to the issue of conflicting evidence. In Part III we show how these theoretical developments arise from important computer vision problems (such as articulated object tracking, data association and object pose estimation) to which, in turn, the evidential formalism is able to provide interesting new solutions. Finally, some initial steps towards a generalization of the notion of total probability to belief functions are taken, in the perspective of endowing the theory of evidence with a complete battery of estimation and inference tools to the benefit of all scientists and practitioners. Visions of a generalized probability theory

Someone pointed to this post from a couple years ago by Uri Simonsohn, who correctly wrote:

This note is just a quick follow-up to our last note on correcting the bias in estimated standard deviations for binomial experiments.

A new minor clean-up release of the anytime package arrived on CRAN overnight. This is the fourteenth release, and follows the 0.3.2 release a good week ago.

By Saurabh Hooda, Hackr.io