By Jeff Jonas, published February 25, 2019

Simple experiment. Read these two related sentences:

I ducked as the bat flew my way.

What an exciting baseball game.

Many people imagine a winged bat when they read the first sentence. After reading the second sentence, they realize it’s a baseball bat. The interesting aspect of this is the reader did not have to re-read the first sentence. Instead the second sentence automagically reclassifies their understanding of the first sentence in real time!

Ever find yourself talking to someone and thinking you know what they mean? Until a few minutes later when you get additional context and realize they meant something entirely different? Same thing.

This is an essential component of human intelligence.

Imagine how psychotic someone would seem if they held onto every first concept — never changing their mind, no matter what new evidence was presented.

This is important because observations often arrive out of order. Did the observations arrive 1, 2, 3 or did they arrive 2, 1, 3? No matter which order the observations arrive, ideally the final understanding should be the same.

As implemented in our Senzing software, we call this sequence neutrality, or sequence neutral computation.

Most information systems lack sequence neutrality. As a consequence, they slowly go psychotic (disconnected from reality resulting in strange behavior). The common remedy is to periodically reload all the data. Imagine that: wrong answers, all week or all month until re-boiling the ocean. It’s bonkers.

So, why don’t more systems build in sequence neutrality? It’s exceptionally hard to do.

Imagine a system with millions of historical records that gets one new record today. If it’s a system with sequence neutrality, it must consider the following: now that I know this new information, would any of my prior assertions be different if I had known this first? If the answer is yes, the system must fix these prior assertions in real time.

At Senzing, we believe sequence neutrality is absolutely essential. We literally spent thousands of hours building the most robust, scalable, sequence neutral algorithms into our AI for Entity Resolution. More about this style of real-time learning and the other unique capabilities can be found here in our Uniquely Senzing white paper.