Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Implementing Callbacks in TensorFlow 2

8 minute read

Published:

Often when training neural networks, we will want to monitor the training process, record metrics, or make changes to the training process. In TensorFlow 2, callbacks can used to call utilities at certain points during training of a neural network. In this post, I’ll describe some of the common use cases of callbacks, show how to implement some of the standard callbacks with the built-in classes, and show how to write custom callbacks to make changes to the training process.

Creating NumPy Arrays

6 minute read

Published:

NumPy arrays are a core part of the numerical computing stack in Python. NumPy provides a large number of functions for creating these arrays, of which np.array is most well known (due to ubiquitous use in tutorials). However, np.array is not always the right function to use. This post will explore some other common array creation functions.

Using Type Hints in Python

3 minute read

Published:

Type hints are annotations in python that indicate the type(s) that are expected as input or return.

Working with Polynomials in Numpy

6 minute read

Published:

Polynomials are an important mathematical building block used in many science and engineering fields. In python, NumPy can be used to perform operations on polynomials.

portfolio

Home Credit Loan Default Analysis

In this analysis, we present findings from loan default data. We provide a model for predicting loan default status and interpretable customer segmentation.

Attrition Data Analysis

In this analysis, we present factors related to attrition. Three top factors are presented and relations to other factors are described. Models for attrition and income are presented along with a discussion on performance. Results of the income modeling are interpreted. Finally, some other trends in the data are described.

publications

Multi-Modal Classification Using Images and Text

Published in SMU Data Science Review, 2021

This paper proposes a method for the integration of natural language understanding in image classification to improve classification accuracy by making use of associated metadata.

Recommended citation: Miller, Stuart J.; Howard, Justin; Adams, Paul; Schwan, Mel; and Slater, Robert (2020) "Multi-Modal Classification Using Images and Text," SMU Data Science Review: Vol. 3 : No. 3, Article 6. https://scholar.smu.edu/datasciencereview/vol3/iss3/6/

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.