I am an adjunct professor of Mathematics, and consult in math, statistics, and data science as well as for small businesses. I also do editorial, design, technical and professional consulting in (literary) publishing, and operate a small international publishing outfit.PreviouslyI am a PhD student at the University of Oregon, researching Deep Learning / Machine Learning emphasizing on the area of deep learning model interpretability and intersections with other core research areas. As part of my research, I worked for UO's NSF-funded Center for Big Learning. Interested in contemporary analytical data science paradigms: statistical, machine learning, and deep learning approaches to modeling and inferring underlying structure from data. My current research interests involve explaining deep learning model predictions which is of both academic and industrial relevance and a particularly important research topic for further industrial applications of deep learning. A deep learning model can only be used confidently in high or medium return/risk contexts (for instance, financial markets or health care decisions) when its users can be reasonably confident in validating that it is generating predictions in an appropriate manner, i.e. that it's learned a to correctly model the underlying phenomena. I've worked on modeling "small" dataset regimes using various standard approaches such as: GLM, SARIMA, MCMC, Bayesian networks, various regression (multivariate polynomial, transformed, gaussian process) and decision forests, density-based clustering, etc. This included the entire pipeline of data capture -> cleaning -> modeling process, including validating model structure, generating predictions and analytics. My Background:Theoretical mathematics and statistics. Currently I primarily work with Python.