Complexity Engineering

Artificial Intuition Finds Unknown Anomalies – Beyond Machine Learning

As weapon systems and fleets become more complex and inter-connected, the number of anomalies that one can face increases rapidly. The problem lies in the fact that:

In highly complex systems the number of potential anomalies can be astronomical.

It is impossible to learn to recognize them all. Besides, systems evolve over time, which means that it may be necessary to continue re-learning old lessons to keep up with the constant changes. This can be very costly, not to say impractical. And quite difficult if someone is, say, firing missiles at you.

Our QCM technology offers a radically innovative alternative to conventional anomaly detection based on Machine Learning. We know (from experience) that when ‘strange things’ happen in complex systems (but not only in complex systems) it is because under the surface a lot of physics is taking place. There are many things that are known that can go wrong, but there also as many that we still haven’t seen:

Machine Learning is often impractical because there are many anomalies that are unknown.

Our Quantitative Complexity Management (QCM) technology is a new form of Artificial Intelligence that reaches beyond the conventional Machine Learning (ML) approach. The main problem with Machine Learning is that it requires numerous examples in order to recognize and classify patterns. While this works well when it comes to recognizing a face or handwriting, in the case of expensive and complex military hardware it is impractical. The fact is that there are not enough anomalies to learn from. Such anomalies can be hugely expensive and nobody – manufacturers or users – can provide a sufficient number of cases from which to learn. Besides, the number of possible anomalies is immense and it is impossible to define and learn to recognize them.

QCM is Artificial Intuition

The key feature of QCM technology is that it is able to recognize the existence of anomalies the first and only time it is confronted with them. It is also able to pinpoint their sources thanks to a technique known as Complexity Profiling. This capability is particularly attractive as it functions independently of the fact that a particular piece of hardware or system is upgraded, modified, or even damaged during a mission. In all such cases ML would not work as one would need to train it anew each time a given system undergoes changes.

QCM, on the other hand, is like human intuition, like instinct. Anyone can feel that something is wrong by listening to a running engine which produces a strange sound without being a trained mechanic.

QCM is Artificial Intuition

With QCM we Find Anomalies you don’t even know you have.

Machine Learning can’t do this.

During years of testing on armoured vehicles, QCM has been shown to not only anticipate anomalies, before they become visible, it can also find anomalies in new vehicles that Quality Control missed.

We have a hardware solution that does all of this in real-time, onboard a vehicle, with no need to transmit data, thereby guaranteeing a high degree of security. It is called the CAHMS:

We anticipate anomalies, onboard, in real time, with no data transmission.

Read more here on Artificial Intuition.

Interested? Email us at info@ontonix.com

http://www.ontonix.com

Established originally in 2005 in the USA, Ontonix is a technology company headquartered in Como, Italy. The unusual technology and solutions developed by Ontonix focus on countering what most threatens safety, advanced products, critical infrastructures, or IT network security - the rapid growth of complexity. In 2007 the company received recognition by being selected as Gartner's Cool Vendor. What makes Ontonix different from all those companies and research centers who claim to manage complexity is that we have a complexity metric. This means that we MEASURE complexity. We detect anomalies in complex defense systems without using Machine Learning for one very good reason: our clients don’t have the luxury of multiple examples of failures necessary to teach software to recognize them. We identify anomalies without having seen them before. Sometimes, you must get it right the first and only time!

0 comments on “Artificial Intuition Finds Unknown Anomalies – Beyond Machine Learning

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: