James Montgomery

Engineer, Entrepreneur, Innovator
Welcome to my blog where I share the latest in my work and interests.
If you like what you see here, please visit the main page of my website to learn more about me!

My Website

Latest Blogs

While I can't talk about the mechanics of most of my work, I love to share the general concepts of what I've learned on my most recent projects. My blog posts are mostly educational in nature and discuss practical and theoretical topics that I find interesting.

Using Experimentation for Sound Decision Making

While collaborating of a pair of reinforcment learning models for digital marketing work, a collegue and I found ourselves explaining our work in experimentation to many of our business collegues. THis blog is for business analysts interested in experimentation.

Read More

Interesting Problems in Decision Theory

In this blog post I cover a few interesting problems from the view of decision theory. A lot of the work I've done in finance boils down to applications of decision theory. It's a topic I love to explore and discuss.

Read More

Facial Recognition

In a past post I discussed building voice recognition models. In this post I go one step further and talk about build a simple, non-deep learning facial recognition model.

Read More

Capture Streaming Network Traffic

I've recently been playing around with machine elarning for personal cyber security. The first step (and subject of this blog post) in my efforts was setting up a capture for streaming network traffic from my router.

Read More

Particle Swarm Optimization

I've spent a lot of the last two weeks working on optimizers for a suite of reinforcement learning models I built and deployed over the last year. While PSO did not end up in any of the production models I deployed, it's one of my favorite methods to think about and discuss.

Read More

Extensions in C

Many of the tools I build are coded in python for end user ease of use. However, python can be slow. Here we explore one potential solution for speeding things up.

Read More

Singular Matrices

Recently, I've been shaping some of my work with Gaussian Processes into an open source package in python. While doing this, I've been dealing with the ever present scourge of singular matrices. Here I hope to share some of my learnings.

Read More

Reasonable Doubt

Reasonable Doubt: Get Onto the Top 35 MNIST Leaderboard by Quantifying Aleatoric Uncertainty is an article I wrote for Medium with my friends and colleagues Bayan Bruss and Jason Wittenbach about bayesian neural networks.

Read More

Distributing in Python

Into the hype around distributed computing? Curious how it might be done in python? I cover the basics of distributed computing in python in this exciting post!

Read More

Random Numbers and Sampling

Ever wonder how computers generate random numbers? Or how computers sample from different probability distirubtions? In this post I cover it all with examples in code.

Read More

Troubleshooting Neural Networks

Over the past few months I've been actively exploring the wide range of neural network flavors. By this I mean feed foward MLPs, CNNs, RNNs (GRU and LSTM), GANs, Seq2Seq, etc. I've collected a lessons learned about how to get these networks working when you hit a road block...and in my experimentation I hit a variety of road blocks!

Read More

Quantifying Model Uncertainty

As many of my collegues know, I'm a huge fan of the cult of bayes. One of the reasons for my fascination with bayesian stats is it's ability to intuitively quanitfy measurement uncertainties. Here I explore methods to quanitfy model uncertainty when making predictions.

Read More

Detecting Fraud with Graphs

Unlike many of my posts, this one is about a rough WIP idea I've had for a while and have just started coding up in my spare time: detecting fake IDs using graphs and edit distance similarities.

Read More

Simple Voice Recognition Model

One of my favorite projects in machine learning from my early days was voice recognition. From GMMs and HMMs to CNNs, there is a lot you can do with audio files. Here I explore a super simple approach to voice recognition.

Read More

Markov Chains and DGAs

A lot of emphasis is put on discriminative models in intro to ML courses. Here I discuss one of my favorite generative models, markov chains, and apply them to a cyber security use case.

Read More

Time Series Modeling Chapter One Part One

The first part in my time series course! Here we'll cover the basic terminology and get comfortable with fundamental concepts.

Read More

Time Series Modeling Intro

A brief overview/table of contents of the multi-part course on time series modeling that I am currently assembling.

Read More

Bayesian Statistics by Example Part One

The first part in my bayesian course! Here we'll cover the basic philosophy of bayesian statistics and get comfortable with high level concepts.

Read More

Bayesian Statistics by Example Intro

A brief overview/table of contents of the multi-part course on bayesian statistics (as it applies to data science and machine learning) that I am currently assembling.

Read More

Contact Me

Email: jamesoneillmontgomery@gmail.com
Linkedin: James Montgomery