© 2016 Agile Data Decisions LLC.                                                                                                                              Proudly created with wix.com

  • YouTube Social  Icon
Site map
More information

Follow us on the social media

Download our flyer

Download a recent "The leading Edge" paper about iQC

MACHINE LEARNING

We use the principles of machine learning to enable the automation of document classification according a given taxonomy, or to extract metadata from them.

While very popular these days, the concept of machine learning is not new, it is actually a very old human dream. 

In the early years of the XIXth century, a machine defeated Napoleon Bonaparte, Benjamin Franklin and several other challengers playing chess. In truth it was a mechanical illusion and the machine wasn't powered by an algorithm ... but by a good chess player hidden inside it! Nevertheless, the idea that a machine could solve a problem faster and better than a human was established.

The early stages of artificial antelligence and machine learning took place during the second world war with Allied and Axis forces trying to break each others' codes. 

In 1959, Arthur Samuel defined machine learning as a "Field of study that gives computers the ability to learn without being explicitly programmed".

It's a very nice definition, but it begs the next question: how can a computer learn? The answer is simply that it learns with data. Computers are able to recognize patterns in the data and make decisions on the basis of the pattern they have recognized.

And the more data they see and the more validations (or refutations) of their decisions they encounter, the better they are at making decisions.

 

Hence came a second definition of a machine learning given by Tom Mitchell in 1997: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E"

In orther words, machine learning capitalizes on user experience and data to improve. It is exactly how our applications work.

At Agile Data Decisions, we consider that if our application has to capitalize on user experience, such an experience has to be excellent and efficient. Therefore we invested heavily in a clear and efficient user interface to make the machine learning training intuitive, fast and easy.

All these principles have been implemented in our first application, iQC, developped for the Oil & Gas industry and covered by a specific patent related to the iQC invention, filed in US under the number 62/265,451.