Posts published by: larry

ML Proofs of Concept Are Hard

ML Proofs of Concept Are Hard

Cartoon showing fragile tower of dependencies

One reason why creating a business case for a Machine Learning project is difficult is that, for virtually any non-trivial task, you’re going to need, from day one of your proof-of-concept, a pretty elaborate data-preparation pipeline and, in most cases, multiple models.

For …

A Simple 3-Step AzureML Pipeline

A Simple 3-Step AzureML Pipeline (Dataprep, Training, and Evaluation)

Get the source code and data on Github

Illustration of pipeline graph

This demonstrates how you create a multistep AzureML pipeline using a series of PythonScriptStep objects.

In this case, the calculation is extremely trivial: predicting Iris species using scikit-learn's Gaussian Naive Bayes. This pipeline …

Longer Orange 30 SLA Printer Assembly & Initial Impressions

Orange 30 Initial Impressions and First Print

I received my Orange 30 in a well-packed box via DHL. My box did not contain a manual, which I think might be an indication that it was among the first few hundred printers shipped. (It did, however, have a USB with what …

From Whalesharks To Leopard Spheres

One of my big weekend projects (for longer than I care to think) has been trying to create a pipeline for identifying individual whalesharks from photos. The project had kind of grown moribund as I repeatedly failed to get any decent level of recognition despite using what I thought was …

Please: Say "Twin" Networks, Not "Siamese" Networks

I'm a big fan of using a pair of identical networks to create output vectors that are then fed into a network that is trained to judge whether it's two input vectors are the same or different.

This is a powerful technique for "low k-shot" comparisons. Most ML techniques that …

Ricky Jay R.I.P

Ricky Jay was one of my heroes. I first became aware of him in the pages of the remarkable “Cards as Weapons,” an oversized paperback that I bought at age 13 because it had a few pictures of topless women in it (you really can’t appreciate how much the …

The Simplest Deep Learning Program That Could Possibly Work

Once upon a time, when I, a C programmer, first learned Smalltalk, I remember lamenting to J.D. Hildebrand "I just don't get it: where's the main()?" Eventually I figured it out, but the lesson remained: Sometimes when learning a new paradigm, what you need isn't a huge tutorial, it's …

"The Deuce" Stinks. A Rant.

I’m a hair’s-breadth away from declaring that “The Deuce,” HBO’s Sunday night “prestige drama” about flesh-peddling and pornos in Times Square and 42nd Street in the mid-70s, is an exercise in trolling, some kind of meta-level commentary on the lack of drama, characterization, or stakes in, y …

Writing to Azure Storage With F#

This last weekend I participated in the "Hack for the Sea" hackathon. As part of that, I needed to store images and structured data to Azure Storage. The process is very straightforward using F#'s async capabilities.

First, you'll need the connection string for your Azure Storage:

Use that to …