The Developer Coefficient

Subjective Bayesian Trust (SBT) This paper is concerned with trust modeling for networked computing systems. Of particular interest to this paper is the observation that trust is a subjective notion that is invisible, implicit and uncertain in nature, therefore it may be suitable for being expressed by subjective probabilities and then modeled on the basis of Bayesian principle. In spite of a few attempts to model trust in the Bayesian paradigm, the field lacks a global comprehensive overview of Bayesian methods and their theoretical connections to other alternatives. This paper presents a study to fill in this gap. It provides a comprehensive review and analysis of the literature, showing that a large deal of existing work, whether or not proposed based on Bayesian principle, can cast into a general Bayesian paradigm termed subjective Bayesian trust (SBT) theory here. The SBT framework can thus act as a general theoretical infrastructure for comparing or analyzing theoretical ties among existing trust models, and for developing novel models. The aim of this study is twofold. One is to gain insights about Bayesian philosophy in modeling trust. The other is to drive current research step ahead in seeking a high-level, abstract way of modeling and evaluating trust. …

IL-Net: Using Expert Knowledge to Guide the Design of Furcated Neural Networks

Power Laws in Deep Learning 2: Universality

In practical machine learning and data science tasks, an ML model is often used to quantify a global, semantically meaningful relationship between two or more values. For example, a hotel chain might want to use ML to optimize their pricing strategy and use a model to estimate the likelyhood of a room being booked at a given price and day of the week. For a relationship like this the assumption is that, all other things being equal, a cheaper price is preferred by a user, so demand is higher at a lower price. However what might easily happen is that upon building the model, the data scientist discovers that the model is behaving unexpectedly: for example the model predicts that on Tuesdays, the clients would rather pay $110 than $100 for a room! The reason is that while there is an expected monotonic relationship between price and the likelyhood of booking, the model is unable to (fully) capture it, due to noisyness of the data and confounds in it.

Gabriel Power writes:

In this paper, we introduce and provide a short overview of nonnegative matrix factorization (NMF). Several aspects of NMF are discussed, namely, the application in hyperspectral imaging, geometry and uniqueness of NMF solutions, complexity, algorithms, and its link with extended formulations of polyhedra. In order to put NMF into perspective, the more general problem class of constrained low-rank matrix approximation problems is first briefly introduced. Introduction to Nonnegative Matrix Factorization

Many of the existing machine learning algorithms, both supervised and unsupervised, depend on the quality of the input characteristics to generate a good model. The amount of these variables is also important, since performance tends to decline as the input dimensionality increases, hence the interest in using feature fusion techniques, able to produce feature sets that are more compact and higher level. A plethora of procedures to fuse original variables for producing new ones has been developed in the past decades. The most basic ones use linear combinations of the original variables, such as PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis), while others find manifold embeddings of lower dimensionality based on non-linear combinations, such as Isomap or LLE (Linear Locally Embedding) techniques. More recently, autoencoders (AEs) have emerged as an alternative to manifold learning for conducting nonlinear feature fusion. Dozens of AE models have been proposed lately, each with its own specific traits. Although many of them can be used to generate reduced feature sets through the fusion of the original ones, there also AEs designed with other applications in mind. The goal of this paper is to provide the reader with a broad view of what an AE is, how they are used for feature fusion, a taxonomy gathering a broad range of models, and how they relate to other classical techniques. In addition, a set of didactic guidelines on how to choose the proper AE for a given task is supplied, together with a discussion of the software tools available. Finally, two case studies illustrate the usage of AEs with datasets of handwritten digits and breast cancer. A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines

Extended Version of Layout Functionality for ‘Base’ and ‘Grid’ Graphics Systems (customLayout)Create complicated drawing areas for multiple plots by combining much simpler layouts. It is an extended version of layout function from the ‘graphics’ …

One thing that is sure to get lost in my long note on macros in R is just how concise and powerful macros are. The problem is macros are concise, but they do a lot for you. So you get bogged down when you explain the joke.