AI, Machine Learning, Reinforcement Learning, and MLOps Articles

Developing a Real-Life Project

Published

Jun 12, 2020

Author

Dr. Phil Winder

CEO

I’m often asked questions in the vain of “how did you figure that out?”. Other times, and I’m less of a fan of these, I get questions like “you estimated X, why did it take 2*X?”, which I respond with a definition of the word estimate. Both of these types of questions are about the research and development process. Non-developers, and especially non-engineers, are often never exposed to the process of research and development. It’s highly non-linear; when it’s going well progress is rapid, but other times you get stuck after falling down a rabbit hole.

A Simple Docker-Based Workflow for Deploying a Machine Learning Model

Published

Apr 24, 2020

Author

Dr. Phil Winder

CEO

In software engineering, the famous quote by Phil Karlton, extended by Martin Fowler goes something like: “There are two hard things in computer science: cache invalidation, naming things, and off-by-one errors.” In data science, there’s one hard thing that towers over all other hard things: deployment.

COVID-19 Hierarchical Bayesian Logistic Model with pymc3

Published

Apr 14, 2020

Author

Dr. Phil Winder

CEO

I have two outstanding tasks from the previous notebooks. The first is that I haven’t iterated over all countries.

COVID-19 Logistic Bayesian Model

Published

Apr 8, 2020

Author

Dr. Phil Winder

CEO

This post builds upon the exponential model created in a previous post. The main issue was that there an exponential model does not include a limit. A logistic model introduces this limit. I also perform some very basic backtesting and future prediction.

COVID-19 Exponential Bayesian Model Backtesting

Published

Apr 8, 2020

Author

Dr. Phil Winder

CEO

This notebook builds upon the exponential bayesian model to implement simple backtesting. The idea here is to hold out data, train a model, and see how well the model is able to predict those results.

COVID-19 Exponential Bayesian Model

Published

Apr 8, 2020

Author

Dr. Phil Winder

CEO

The purposes of this notebook is to provide initial experience with the pymc3 library for the purpose of modeling and forecasting COVID-19 virus summary statistics. This model is very simple, and therefore not very accurate, but serves as a good introduction to the topic.

COVID-19 Response: Athena Project and an Introduction Bayesian Analysis

Published

Apr 8, 2020

Author

Dr. Phil Winder

CEO

Over the next couple of weeks I will be using Bayesian analysis to model the spread of COVID-19. Inspired by Alex Stage who started the Athena Project, I have committed Winder.AI to helping Athena reach its goals.

How to Start a Data Science Project With No or Little Data

Published

Feb 26, 2020

Author

Hajar Khizou

Associate Data Science Content Editor

Data is an essential asset of modern business. It empowers companies by surfacing unique insights about their customers and creates actionable products. The more data you possess, the better you meet and exceed your customers’ expectations.

Keep it Clean: Why Bad Data Ruins Projects and How to Fix it

Published

Oct 24, 2019

Author

Dr. Phil Winder

CEO

Abstract

The Internet is full of examples of how to train models. But the reality is that industrial projects spend the majority of the time working with data. The largest improvements in performance can often be found through improving the underlying data.

Fast Time-Series Filters in Python

Published

Oct 4, 2019

Author

Dr. Phil Winder

CEO

Time-series (TS) filters are often used in digital signal processing for distributed acoustic sensing (DAS). The goal is to remove a subset of frequencies from a digitised TS signal. To filter a signal you must touch all of the data and perform a convolution. This is a slow process when you have a large amount of data. The purpose of this post is to investigate which filters are fastest in Python.